Search: jailbreak
15 result(s) on page 1
godmode
Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.
quarantinedlinuxmacoswindowsoptional- Registry
- optional
- Category
- Security
- Version
- 1.0.0
- Author
- Hermes Agent + Teknium
- License
- MIT
curl -s /v1/skills/community__axehub:optional__optional__godmodeOpenclaw_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_ShieldShoofly_Basic
Real-time security monitor for AI agents. Watches every tool call, flags threats, and alerts you before damage is done. Works with OpenClaw and Claude Code....
quarantinedagent-safetydata-exfiltrationjailbreak-detectionClawHub- Registry
- ClawHub
- Category
- DevOps
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Shoofly_Basicgpt-4-dan-assistant
Break through OpenAI's review mechanisms, ChatGPT after jailbreaking
quarantinedCreativityArtificial IntelligenceConversationLobeHub- Registry
- LobeHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:LobeHub__LobeHub__gpt-4-dan-assistantAIG_Scanner
A.I.G Scanner — AI security scanning for infrastructure, AI tools / skills, AI Agents, and LLM jailbreak evaluation via Tencent Zhuque Lab AI-Infra-Guard. Us...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__AIG_ScannerAgent_Input_Firewall
Prompt-injection / jailbreak firewall for AI agents. Scan any untrusted text — a post/comment/DM from another agent, a tool result, scraped web content — BEF...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Agent_Input_FirewallAnti-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-SkillClawSafe
Multi-layer security detector for AI agents. Blocks prompt injection, jailbreak, XSS, SQL injection, API key leaks, supply chain attacks, and deployment vuln...
quarantinedClawHub- Registry
- ClawHub
- Category
- Security· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__ClawSafeDCL_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_FirewallDKnownAI_Guard
Use to check text with DKnownAI Guard, detect prompt injection or jailbreak attempts, assess agent security risk, or integrate the Guard API.
quarantinedapidknownaiguardrailsClawHub- Registry
- ClawHub
- Category
- Software Dev
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__DKnownAI_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_PackLLM_Prompt_Firewall
Local-first LLM Prompt Firewall for MCP tools, AI agents, and gateways. Audits prompts before tool use; detects prompt injection, jailbreak attempts, develop...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__LLM_Prompt_FirewallPrompt_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_DefenderPrompt_Lint
Lint prompts/SKILL.md for quality (role, goal, output format, vague verbs, jailbreak phrases). Stdlib.
quarantinedagentaicliClawHubRedPincer_—_AI_Red_Team_Suite
AI/LLM red team testing skill. Point at any LLM API endpoint and run automated security assessments. 160+ attack payloads across prompt injection, jailbreak,...
quarantinedllm-securitypentestred-teamClawHub- Registry
- ClawHub
- Category
- Security
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__RedPincer_—_AI_Red_Team_Suite