sigil-scan

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

• Third-party content exposure detected (low risk: 0.10). The workflow scans arbitrary remote repositories, packages, and URLs (git clone, npm, pip, fetch), which exposes the agent to outsider-authored free text when analyzing external code and packages.

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

• Potentially malicious external URL detected (high risk: 0.70). The setup script downloads a binary release from GitHub repository NOMARJ/sigil via an unpinned tag lookup and executes it, which constitutes an unverifiable operational dependency with weak/unknown publisher provenance.