infsh-cli

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly shows running public web-search and extractor apps (e.g., "belt app run tavily/search-assistant" in Quick Examples and references/app-discovery.md listing Tavily/Exa search) and includes Twitter automation apps (x/post-tweet), which means the skill instructs the agent to fetch and ingest open/public third-party (web and social) content that could influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs users to run a remote installer via "curl -fsSL https://cli.inference.sh | sh", which fetches and executes code from https://cli.inference.sh at runtime and is required to use the CLI, so that URL is a high-risk runtime dependency.