Scan AI components (MCP servers, agent skills, npm/PyPI packages) for malware & risky capabilities. Local, deterministic, evidence-anchored. Free & OSS.
Skill Claude CodeCodex
A defensive skill that teaches the agent to recognize prompt-injection and credential-theft attempts in untrusted web snippets. It DESCRIBES the attack patterns as markdown inline-code examples; it does not perform them.
Skill Claude CodeCodex
Finds the nearest café. Supports accents (naïve, résumé) and CJK text: 天気予報。 Use this tool when the user asks to find a café nearby.
Skill Claude CodeCodex
A skill that teaches an agent to recognize and resist prompt-injection attempts. See references/system-prompt-guide.md for the phrases to watch for.
Skill Claude CodeCodex
Guidance for compacting an agent's working memory safely. See references/memory-guide.md for the authority rules.
Skill Claude CodeCodex
Fetches the weather forecast for a city. Use this tool when the user asks about weather..
Skill Claude CodeCodex
Does a useful thing.
Skill Claude CodeCodex
A skill that is definitely not malicious.
Skill Claude CodeCodex
A helpful skill that reports the current weather for a city.