rails-gem-finder

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

• Third-party content exposure detected (medium risk: 0.30). The workflow explicitly instructs the agent to perform web searches (RubyGems/GitHub/community) and then fetch and read README content from promising gems via webFetch, meaning outsider-authored free text from those external sources is ingested at runtime.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly instructs the agent to use webFetch at runtime to read gem READMEs and other external pages (e.g., https://rubygems.org/gems/), so fetched external content will be injected into and directly influence the agent's outputs.