aeon-update

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

• Third-party content exposure detected (low risk: 0.10). The skill’s required runtime workflow (gh api compare/contents fetches in steps S4 and S6) ingests free text from an outsider-authored GitHub repo (commit messages and file contents) fetched from UPSTREAM via gh api repos/${UPSTREAM}/compare/... and gh api repos/${UPSTREAM}/contents/$1?ref=$2.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill downloads and executes a third-party release from the GitHub repo "alexverify/eyebrow" at runtime via the command gh release download v0.4.1 -R alexverify/eyebrow ... (it fetches the tarball, verifies SHA256, extracts and may run the eyebrow binary), which is remote code fetched-and-executed during runs.