netresearch-branding
Warn
Audited by Snyk on May 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's checkpoints.yaml (llm_reviews NB-20) explicitly instructs the agent to call the GitHub API (gh api repos/{owner}/{repo} --jq '.description') and base PASS/FAIL decisions on the repository description — an untrusted, user-provided third-party input that the agent is expected to read and act on.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata