source-triage
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). The skill’s Flow 1 sync path fetches outsider-authored free text from public GitHub sources at runtime (e.g.,
gh issue list/gh api graphqlfor repo issues & discussions bodies/titles, andgh api repos/<owner/name>/commitsfor commit subjects), which is then ingested into the agent’s LLM context during reconciliation/triage.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata