merge-buddy
Warn
Audited by Snyk on Jul 5, 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). At runtime the skill calls
gh pr listandgh pr checks, which ingest outsider-authored PR metadata and check names/states (e.g., PR titles/authors/labels and check results) into the agent’s LLM context for classification/reporting.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata