entropy-check

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads GitHub issues and PR comments/files via gh issue list and gh api pulls/.../files, exposing the agent to outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installation via npx skills add fellowship-dev/dogfooded-skills/skills/ops/entropy-check, which retrieves and installs executable code from an external GitHub repository under an individual/community organization without enforced integrity digests, constituting a weak operational dependency.