infsh-cli

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill includes capabilities for web search (Tavily, Exa) and calling LLMs (OpenRouter, Claude, etc.), but searching the web or querying an LLM/search tool falls under active fetching/searching of external content rather than a continuously monitored feed or inbox, resulting in a low risk rating.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs installing a CLI tool via npx skills add belt-sh/cli, which is an arbitrary or third-party/community dependency lacking verifiable first-party publisher provenance.