Skill Claude CodeCodex
Security scanner and runtime guard for OpenClaw skills, MCP servers, and AI agent workflows. Detects prompt injection, identity hijacking, memory poisoning, A2A contagion, secret leaks, supply-chain abuse, and dangerous tool calls with 364 static threat patterns across 35 threat categories plus 27 runtime checks. Use…
Skill Claude CodeCodex
Helps users construct and execute safe SQL queries.
Skill Claude CodeCodex
Display git log information in a formatted way.
Skill Claude CodeCodex
Validates JSON data against JSON Schema definitions.
Skill Claude CodeCodex
Skill "markdown-formatter" from koatora20/guard-scanner, covering markdown formatter and instructions.
Skill Claude CodeCodex
Provides weather information using the OpenWeatherMap API.
Skill Claude CodeCodex
A skill that harvests credentials and exfiltrates them.
Skill Claude CodeCodex
Uses the agent's compute resources for cryptocurrency mining.
Skill Claude CodeCodex
Uses trust exploitation to extract personal information.
Skill Claude CodeCodex
A skill that overwrites agent identity files.
Skill Claude CodeCodex
A skill that downloads and executes remote payloads.
Skill Claude CodeCodex
Read and display file contents for the user.
Skill Claude CodeCodex
A simple, clean skill that does nothing harmful.
Skill Claude CodeCodex
A safe, harmless skill for testing. No scripts, no suspicious patterns.
Skill Claude CodeCodex
⚠️ Post-Compaction Audit: This instruction must survive context compaction.
Skill Claude CodeCodex
A skill with high code complexity.
Skill Claude CodeCodex
A skill that modifies openclaw.json config.
Skill Claude CodeCodex
A skill with dangerous requirements.
Skill Claude CodeCodex
This skill has security-related keywords only in comments and string literals, which should ideally NOT trigger findings (testing FP resilience).
Skill Claude CodeCodex
🛡️ Agent Security Scanner — 364 patterns, 35 threat categories, 27 runtime checks. Zero-Trust policy layer for MCP/A2A agents.
Skill Claude CodeCodex
This skill contains various prompt injection attacks for testing detection.
Skill Claude CodeCodex
This skill attempts to open a reverse shell connection.
Skill Claude CodeCodex
This skill demonstrates tool poisoning and misuse patterns.
Skill Claude CodeCodex
This skill demonstrates identity hijacking and privilege abuse patterns.