Search: prompt-injection-defense
100 result(s) on page 1
Defense
A comprehensive AI agent skill for anyone facing criminal charges, civil lawsuits, or regulatory investigations. Helps you understand what you are facing, pr...
quarantinedcriminaldefenselawsuitClawHubIndirect_Prompt_Injection_Defense
Detect and reject indirect prompt injection attacks when reading external content (social media posts, comments, documents, emails, web pages, user uploads). Use this skill BEFORE processing any untrusted external content to identify manipulation attempts that hijack goals, ex…
quarantinedClawHub- Registry
- ClawHub
- Category
- Security· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Indirect_Prompt_Injection_DefensePrompt_Injection_Defense
Harden agent sessions against prompt injection from untrusted content. Use when the agent reads web search results, emails, downloaded files, PDFs, or any ex...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Prompt_Injection_DefenseActive_Defense_Sentinal
Defensive triage skill for OpenClaw, Hermes Agent, host integrity, and OpenClaw skill-supply-chain scanning. Detects prompt injection, session drift, context...
quarantinedbrowserdefensehermesClawHub- Registry
- ClawHub
- Category
- DevOps
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Active_Defense_SentinalPrompt_defense
Detect and block prompt injection attacks in emails. Use when reading, processing, or summarizing emails. Scans for fake system outputs, planted thinking blocks, instruction hijacking, and other injection patterns. Requires user confirmation before acting on any instructions f…
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Prompt_defensePrompt_Injection_Guard
Prompt injection defense. Detect and block malicious prompts, protect system instructions, sanitize user input.
quarantinedClawHub- Registry
- ClawHub
- Category
- Security· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Prompt_Injection_GuardAnti-Injection-Skill
Detect prompt injection, jailbreak, role-hijack, and system extraction attempts. Applies multi-layer defense with semantic analysis and penalty scoring.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Anti-Injection-SkillBlack_Fortress
Pre-installation agentic sandboxing protocol. 5-layer defense: semantic neutralization, hard quarantine, kernel ground-truth, trusted output rendering, and s...
quarantinedagent-isolationprompt-injection-defensesandboxingClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Black_Fortress1-SEC:_All-in-One_Cybersecurity_for_AI_Agent_Hosts
Install, configure, and manage 1-SEC — an open-source, all-in-one cybersecurity platform (16 modules, single binary) on Linux servers and VPS instances. Use...
quarantinedai-agentcybersecurityendpoint-defenseClawHub- Registry
- ClawHub
- Category
- AI Agents
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__1-SEC:_All-in-One_Cybersecurity_for_AI_Agent_HostsOpenExec_—_Deterministic_Execution_Boundary_for_Agent_Systems
Source-distributed deterministic execution service with pinned dependencies. Runs only with a signed approval artifact (ClawShield mode) and emits verifiable...
quarantinedagent-governanceagent-runtimeai-guardrailsClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__OpenExec_—_Deterministic_Execution_Boundary_for_Agent_SystemsArmarius_-_Prompt_Injection_Blocker
One click, always on. Zero extra API calls. Neutralizes prompt injection the moment it arrives. Never interrupts your work. No setup, no code required.
quarantinedagentsalways-onpreventionClawHub- Registry
- ClawHub
- Category
- AI Agents
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Armarius_-_Prompt_Injection_BlockerAgent_Dispute_Resolution_&_Chargeback_Defense
Agent Dispute Resolution & Chargeback Defense. Build automated dispute resolution pipelines, implement Verifiable Intent-compatible evidence chains, and defe...
quarantinedai-agentchargebacksdisputesClawHub- Registry
- ClawHub
- Category
- AI Agents
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Agent_Dispute_Resolution_&_Chargeback_DefenseDefense_Rehearsal
Use when preparing for, rehearsing, or debriefing an academic defense — proposal/mid-term/graduation — e.g. says '模拟答辩'、'生成提问清单'、'帮我演练答辩'、'复盘我的表达'、'defense r...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Defense_RehearsalMalware_Defense_Roadmap
Comprehensive security assessment and implementation planning platform that generates personalized malware defense roadmaps based on organizational profile a...
quarantinedClawHub- Registry
- ClawHub
- Category
- Security· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Malware_Defense_RoadmapPaper_Defense_Q&A_+_Code_Audit_+_Visual_Answer_Cards
Prepare evidence-grounded computer science paper defense Q&A, code/training audit, reviewer-style attack surfaces, mock-defense scripts, backup-slide plans,...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Paper_Defense_Q&A_+_Code_Audit_+_Visual_Answer_CardsSelf_Defense_Fundamentals
Personal safety awareness and basic physical self-defense techniques. Use when someone wants to feel safer in public, works late shifts, walks alone, or want...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Self_Defense_FundamentalsThreat_Assessment_Defense_Guide
Generate comprehensive cybersecurity threat assessments and defense guides. Use when evaluating threat landscapes, building defense strategies, ransomware pr...
quarantinedClawHub- Registry
- ClawHub
- Category
- Security· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Threat_Assessment_Defense_GuideUplo_Defense
AI-powered defense knowledge management. Search mission documentation, logistics records, personnel data, and ITAR-controlled information with structured ext...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Uplo_Defensedefense_lawyer
AI-powered criminal defense assistant for Chinese legal system - provides case analysis, defense strategy formulation, evidence assessment, and legal documen...
quarantinedClawHub- Registry
- ClawHub
- Category
- Domain· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__defense_lawyerthesis-defense-qa-generator
Generate likely thesis, dissertation, undergraduate paper, or graduation-project defense questions and strong reference answers from a user's complete thesis...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__thesis-defense-qa-generatorPrompt_Guard
650+ pattern AI agent security defense covering prompt injection, supply chain injection, memory poisoning, action gate bypass, unicode steganography, cascad...
quarantinedClawHub- Registry
- ClawHub
- Category
- Security· inferred
- Version
- 1.0.5
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Prompt_GuardAI-Warden_—_Prompt_Injection_Protection
Install, configure, and manage the AI-Warden prompt injection protection plugin for OpenClaw. Publisher: AI-Warden (ai-warden.io). Source: github.com/ai-ward...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__AI-Warden_—_Prompt_Injection_ProtectionAOI_Prompt_Injection_Sentinel
Detects and scores prompt injection attempts in text, outputting severity, action, and matched rules without external calls or secret handling.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__AOI_Prompt_Injection_SentinelClawDefender_-_OpenClaw_Security_-_Prompt_injection,_rogue_skills_etc
Security scanner and input sanitizer for AI agents. Detects prompt injection, command injection, SSRF, credential exfiltration, and path traversal attacks. Use when (1) installing new skills from ClawHub, (2) processing external input like emails, calendar events, Trello cards…
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__ClawDefender_-_OpenClaw_Security_-_Prompt_injection,_rogue_skills_etcinjection
Detect prompt injection attacks and adversarial inputs in user text before passing it to your LLM. Use when you need to validate or screen user-provided text...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Detector_of_prompt__injectionPROMPT_INJECTION_PROTECTION
Protects against prompt injection attacks by sanitizing, validating, and securely processing untrusted external content from websites, emails, and documents.
quarantinedClawHub- Registry
- ClawHub
- Category
- Security· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__PROMPT_INJECTION_PROTECTIONPrompt_Injection_Tester
Test LLM applications for prompt injection vulnerabilities — run attack simulations, evaluate defenses, and generate hardening recommendations for AI systems.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Prompt_Injection_TesterPrompt_injection_detection_skill
Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message references system prompts, hidden instructions, or internal configuration, (3) receiving messag…
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Prompt_injection_detection_skillAi_Scam_Defense
Identify and defend against AI-powered scams including deepfakes, voice cloning, AI phishing, and fake job offers. Use when someone received a suspicious cal...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Ai_Scam_DefenseHallucination_Guard_—_4-Layer_AI_Fabrication_Defense
Detect and prevent AI agent hallucinations during task execution. Use when: (1) an agent claims to have created files, commits, or artifacts — verify them, (...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Hallucination_Guard_—_4-Layer_AI_Fabrication_DefenseMortgage_—_Rate_&_Terms_Anchoring_(Defense_+_Framing)
Activate when: a borrower anchors on a headline/teaser rate they saw; presenting rate+points+APR trade-offs; competitor 'lowball' quote; 'why is your rate hi...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Mortgage_—_Rate_&_Terms_Anchoring_(Defense_+_Framing)Nm_Leyline_Additive_Bias_Defense
Inverts burden of proof for code additions
quarantinedClawHub- Registry
- ClawHub
- Category
- Security· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Nm_Leyline_Additive_Bias_DefenseVps_Proactive_Defense
Harden a public VPS running OpenClaw: CrowdSec + fail2ban + Suricata + honeypot + GeoIP, with exact commands to verify and respond. / 加固运行 OpenClaw 的公网 VPS：C...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Vps_Proactive_DefenseWage_Theft_Defense
Tools for identifying, documenting, and recovering stolen wages. Use when someone suspects unpaid overtime, tip theft, minimum wage violations, off-the-clock...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Wage_Theft_Defensedefense-in-depth-validation
Indexed by skills.sh from obra/superpowers-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.5
- Author
- obra
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__defense-in-depth-validationtower-defense
Indexed by skills.sh from gamedev-skills/awesome-gamedev-agent-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- gamedev-skills
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__tower-defensePrompt_Injection_Removal
A secure sanitization system to strip instructions from external content.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Prompt_Injection_Removalllm-prompt-injection
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__llm-prompt-injectionPrompt_Shield_Publish
Prompt Injection Firewall for AI agents. 113 detection patterns, 14 threat categories, zero dependencies. Protects against fake authority, command injection, memory poisoning, skill malware, crypto spam, and more. Hash-chain tamper-proof whitelist with mandatory peer review. C…
quarantinedagent-safetyfirewallprompt-injectionClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Prompt_Shield_PublishPrompt_Defender
Scan AI prompts for injection, jailbreak, and sensitive data leak risks
quarantinedaiprompt-injectionsecurityClawHub- Registry
- ClawHub
- Category
- AI Agents
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Prompt_DefenderOpenclaw_Prompt_Shield
Local input-hardening scanner for OpenClaw agents. Pattern-based detection across 9 categories of LLM input risks, with combined-signal scoring and caller-su...
quarantinedagent-safetyguardrailindirect-injectionClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Openclaw_Prompt_Shieldyundaodev-1
A Chinese criminal law expert with many years of experience in criminal defense practice, knowledgeable in criminal law and criminal procedure law theory.
quarantinedCriminal DefenseLobeHub- Registry
- LobeHub
- Category
- Domain· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:LobeHub__LobeHub__yundaodev-1Golang_Dependency_Injection
Comprehensive guide for dependency injection (DI) in Golang. Covers why DI matters (testability, loose coupling, separation of concerns, lifecycle management...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Golang_Dependency_InjectionPydantic_Ai_Dependency_Injection
Implement dependency injection in PydanticAI agents using RunContext and deps_type. Use when agents need database connections, API clients, user context, or...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Pydantic_Ai_Dependency_InjectionSQL_Injection_Testing
Perform authorized security tests to detect, exploit, and validate defenses against SQL injection vulnerabilities in web applications.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__SQL_Injection_TestingAI_Safety_Rails
Automatically configures safety rules, trust levels, prompt injection defense, and approval workflows to secure OpenClaw agent actions.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__AI_Safety_RailsAgent_Ops_Framework
AI agent operations reference — multi-agent architectures, ReAct and chain-of-thought patterns, tool-use conventions, prompt injection defense, and evaluatio...
quarantinedproductivityClawHub- Registry
- ClawHub
- Category
- Productivity
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Agent_Ops_FrameworkAgent_Security_Hardening
Security hardening patterns for production AI agents. Covers prompt injection defense (7 rules), data boundary enforcement, read-only defaults for external i...
quarantinedClawHub- Registry
- ClawHub
- Category
- Security· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Agent_Security_HardeningClawGuard-Shield
ClawGuard Shield v3 - Active defense with prompt injection detection, intent validation, zero-width character detection, and intent integrity verification
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__ClawGuard-ShieldEridian_Carapace
Agent security hardening and prompt injection defense for OpenClaw. Protects against ClawHavoc-style attacks including prompt injection, data exfiltration, credential theft, and unauthorized operations. Runtime protection that complements pre-installation skill scanners like C…
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Eridian_CarapaceIronClaw_Security_Guard
Add lightweight defense-in-depth guardrails to OpenClaw with dangerous-command blocking, prompt-injection detection, secret redaction, and audit logging.
quarantinedClawHub- Registry
- ClawHub
- Category
- Security· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__IronClaw_Security_GuardOpenclaw
Secure key management for AI agents. Use when handling private keys, API secrets, wallet credentials, or when building systems that need agent-controlled funds. Covers secure storage, session keys, leak prevention, and prompt injection defense.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.59
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__OpenclawOpenclaw_Bastion
Prompt injection defense for agent workspaces. Scan files for injection attempts, analyze content boundaries, detect hidden instructions, and maintain command allowlists. Free alert layer — upgrade to openclaw-bastion-pro for active blocking, sanitization, and runtime enforcem…
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Openclaw_BastionOperation_Quarantine
Prompt injection defense for OpenClaw agents. Scans emails and skill installations through a two-phase security pipeline (pattern matching + optional LLM ana...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Operation_QuarantineSecurity_Hardening
Security audit and hardening for AI agents — credential hygiene, secret scanning, prompt injection defense, data leakage prevention, and privacy zones.
quarantinedClawHub- Registry
- ClawHub
- Category
- Security· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Security_Hardeningsmart-security
Advanced prompt injection defense with multi-layer protection, memory integrity, and tool security wrapper. OWASP LLM Top 10 2026 compliant.
quarantinedClawHub- Registry
- ClawHub
- Category
- Security· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__smart-securityPrompt_Safe
Token-safe prompt assembly with memory orchestration. Use for any agent that needs to construct LLM prompts with memory retrieval. Guarantees no API failure due to token overflow. Implements two-phase context construction, memory safety valve, and hard limits on memory injection.
quarantinedmemoryprompt-engineeringtoken-safetyClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Prompt_SafeAegis_Shield
Prompt-injection and data-exfiltration screening for untrusted text. Use before summarizing web/email/social content, before replying, and especially before writing anything to memory. Provides a safe memory append workflow (scan → lint → accept or quarantine).
quarantinedmemoryopenclawprompt-injectionClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Aegis_ShieldAgent_Mail_Guard_—_Email_Sanitizer_for_AI_Agents
Sanitize email and calendar content before it reaches your AI agent's context window. Blocks prompt injection, markdown image exfiltration, invisible unicode...
quarantinedemailopenclawprompt-injectionClawHub- Registry
- ClawHub
- Category
- Productivity
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Agent_Mail_Guard_—_Email_Sanitizer_for_AI_AgentsAgent_Runtime_Security
Complete OpenClaw Agent Security Hardening - Protects against data leaks (storage security) and prompt injection (runtime security). Use for initial setup, s...
quarantinedagent-protectioncommand-safetyprompt-injectionClawHub- Registry
- ClawHub
- Category
- Security· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Agent_Runtime_SecurityClawProof_Security_Scanner
Enterprise-grade security for OpenClaw - blocks malicious skills, detects hallucinated packages, and prevents prompt injection attacks. Powered by agent-secu...
quarantinedai-safetyast-analysisauto-fixClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__ClawProof_Security_ScannerClawShield
OpenClaw security audit + prompt injection detector. Scans gateway/vulns/cron/PI patterns. Use for frenzy-proofing installs.
quarantinedAPI securityAuditHacker ProtectionClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__ClawShieldEmail_Security
Protect AI agents from email-based attacks including prompt injection, sender spoofing, malicious attachments, and social engineering. Use when processing emails, reading email content, executing email-based commands, or any interaction with email data. Provides sender verific…
quarantinedagent-safetyattachmentsdkimClawHub- Registry
- ClawHub
- Category
- Productivity
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Email_SecurityGuard_Scanner
Security scanner and runtime guard for OpenClaw skills, MCP servers, and AI agent workflows. Detects prompt injection, identity hijacking, memory poisoning,...
quarantinedagent-securitymcpopenclawClawHub- Registry
- ClawHub
- Category
- MCP
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Guard_ScannerMeerkat_Governance
AI governance API with two endpoints. Shield scans untrusted content for prompt injection and threats. Verify checks AI output for hallucinations, numerical...
quarantinedgovernancehallucination-detectionprompt-injectionClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Meerkat_GovernanceOpenClaw_Hardener
Harden OpenClaw (workspace + ~/.openclaw): run openclaw security audit, catch prompt-injection/exfil risks, scan for secrets, and apply safe fixes (chmod/exec-bit cleanup). Includes optional config.patch planning to reduce attack surface.
quarantinedauditclawhubdevsecopsClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__OpenClaw_HardenerSecurity_Audit_(Sona)
Fail-closed security auditing for OpenClaw/ClawHub skills & repos: trufflehog secrets scanning, semgrep SAST, prompt-injection/persistence signals, and supply-chain hygiene checks before enabling or installing.
quarantinedauditclawhubdevsecopsClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Security_Audit_(Sona)SentiClaw
Runtime AI security for OpenClaw agents. Protects against prompt injection, identity spoofing, PII leakage, and runtime abuse. Drop-in 6-layer security middl...
quarantinedidentityopenclawpiiClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__SentiClawVeridicusScan_MCP_Analyst
Use when the user wants to inspect a prompt, local file, or public HTTPS URL with VeridicusScan through its MCP bridge, triage prompt-injection or hidden-ins...
quarantinedmcpprompt-injectionsecurityClawHub- Registry
- ClawHub
- Category
- MCP
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__VeridicusScan_MCP_AnalystZugaShield_Security_Scanner
7-layer AI security scanner for OpenClaw. Blocks prompt injection, SSRF, command injection, data leakage, and memory poisoning across ALL channels (Signal, T...
quarantinedai-safetymcpprompt-injectionClawHub- Registry
- ClawHub
- Category
- MCP
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__ZugaShield_Security_Scannermerlin-security-sentinel
Use this skill when the user asks about securing their OpenClaw installation, configuring AI agents safely, understanding prompt injection risks, dealing wit...
quarantinedagent-safetyprompt-injectionsecurityClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__merlin-security-sentinelmlayer-guard
Runtime prompt injection detection for AI agents. Checks tool outputs for hidden instructions before your agent acts on them. 98% detection rate on agent att...
quarantinedguardrailprompt-injectionsecurityClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__mlayer-guardcmdi-command-injection
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__cmdi-command-injectioncrlf-injection
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Category
- Security· inferred
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__crlf-injectioncsv-formula-injection
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__csv-formula-injectiondangling-markup-injection
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__dangling-markup-injectiondependency-injection-patterns
Indexed by skills.sh from aaronontheweb/dotnet-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- aaronontheweb
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__dependency-injection-patternsemail-header-injection
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__email-header-injectionexploiting-sql-injection-vulnerabilities
Indexed by skills.sh from mukul975/anthropic-cybersecurity-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- mukul975
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__exploiting-sql-injection-vulnerabilitiesexpression-language-injection
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__expression-language-injectiongolang-dependency-injection
Indexed by skills.sh from samber/cc-skills-golang
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- samber
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__golang-dependency-injectioninjection-checking
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__injection-checkingjndi-injection
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Category
- Security· inferred
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__jndi-injectionmacos-process-injection
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__macos-process-injectionmaui-dependency-injection
Indexed by skills.sh from dotnet/skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- dotnet
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__maui-dependency-injectionmicrosoft-extensions-dependency-injection
Indexed by skills.sh from wshaddix/dotnet-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- wshaddix
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__microsoft-extensions-dependency-injectionnosql-injection
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Category
- Security· inferred
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__nosql-injectionspring-boot-dependency-injection
Indexed by skills.sh from giuseppe-trisciuoglio/developer-kit
quarantinedskills.sh- Registry
- skills.sh
- Category
- Software Development· inferred
- Version
- 1.0.0
- Author
- giuseppe-trisciuoglio
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__spring-boot-dependency-injectionsql-injection-prevention
Indexed by skills.sh from aj-geddes/useful-ai-prompts
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- aj-geddes
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__sql-injection-preventionsql-injection-testing
Indexed by skills.sh from davila7/claude-code-templates
quarantinedskills.sh- Registry
- skills.sh
- Category
- Software Development· inferred
- Version
- 1.0.5
- Author
- davila7
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__sql-injection-testingsqli-sql-injection
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__sqli-sql-injectionssti-server-side-template-injection
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__ssti-server-side-template-injectionxslt-injection
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Category
- Security· inferred
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__xslt-injectionDeepsafe_Scan
Preflight security scanner for AI coding agents — scans deployment config, skills/MCP servers, memory/sessions, and AI agent config files (hooks injection) f...
quarantinedauditdeceptiondeepsafeClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Deepsafe_ScanSkill_Security_Auditor
Command-line security analyzer for ClawHub skills. Run analyze-skill.sh to scan SKILL.md files for malicious patterns, credential leaks, and C2 infrastructure before installation. Includes threat intelligence database with 20+ detection patterns.
quarantinedauditcli-tooldefenseClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Skill_Security_AuditorYiDunAppDefense
易盾应用加固 - AI Agent Skill for multi-platform app protection
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__YiDunAppDefenseDCL_Prompt_Firewall
Instruction-only input-layer shield for AI agents and LLM pipelines. Detects prompt injection, jailbreak attempts, instruction override, role-switch attacks,...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__DCL_Prompt_FirewallDuru_Prompt_Shield
Minimal anti-prompt-injection guardrail for OpenClaw agents. Use when handling untrusted external content (web pages, emails, tool output, documents), before...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Duru_Prompt_ShieldEli_Prompt_Guard
Automatically detects and blocks prompt injection attempts across multiple platforms to protect against unauthorized commands and data leaks.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Eli_Prompt_GuardFirm_Prompt_Security_Pack
Prompt injection and jailbreak detection pack. 16 compiled regex patterns across 3 severity levels (CRITICAL, HIGH, MEDIUM). Supports single-prompt and batch...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Firm_Prompt_Security_Pack