autopilot
Warn
Audited by Snyk on May 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill explicitly calls the public GitHub Releases API (see the
/autopilot versionand Update check steps that run curl against https://api.github.com/repos/PresentJay/autopilot-skills/releases/latest and parse "tag_name") and uses that untrusted, user-controlled release data to decide whether to prompt for or automatically run an update (e.g.,npx skills update ...), so third-party release content can materially influence the agent's actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata