project-artifact
Warn
Audited by Snyk on Jun 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the LLM context when the skill “Pull[s] whatever the domain gives you cheaply — always live” for software projects, including PR bodies/review thread content via
gh pr view <n> --json bodyand GraphQL review thread data; those are third-party authored texts (outsider) that the agent summarizes into the published HTML/artifact-state.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata