codex-autoresearch-loop

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

• Third-party content exposure detected (low risk: 0.10). The skill includes a pivot protocol that performs web searches when stalled, but this is an active search/fetch of external references rather than a monitored outsider-submitted feed.

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

• Potentially malicious external URL detected (medium risk: 0.30). The repository URL provided in the installation instructions is an unofficial third-party GitHub repository, constituting an unverified operational dependency.