new-project
Warn
Audited by Snyk on Sep 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The workflow fetches a remote instruction file from GitHub (
https://raw.githubusercontent.com/stonega/harness/refs/heads/main/_AGENTS.md) at runtime, which exposes the agent to outsider-authored free text from an unvetted external repository.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill fetches an external remote file (
https://raw.githubusercontent.com/stonega/harness/refs/heads/main/_AGENTS.md) at runtime during initialization, which constitutes an unofficial external operational dependency with high risk provenance.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata