web-search

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

• Third-party content exposure detected (low risk: 0.10). The skill performs web search and URL content extraction via Tavily and Exa, which ingests outsider-authored web content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installation of a CLI tool via npx skills add belt-sh/cli, which fetches and installs code from an unverified third-party GitHub org ("belt-sh") that is then executed throughout the skill via the belt command, constituting a weak/unverified operational dependency.