github-hunter
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly searches and fetches content from public GitHub (e.g., https://github.com/search, https://api.github.com/repos/{owner}/{name} and the README endpoint) and parses repository metadata and README text—untrusted, user-generated third-party content—into its scoring and integration workflows, which could enable indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill includes an explicit runtime curl example that posts to the GitHub Actions dispatch endpoint https://api.github.com/repos/breverdbidder/life-os/actions/workflows/insert_insight.yml/dispatches which, when invoked at runtime, would trigger/execute remote workflow code outside the agent's control.
Audit Metadata