ha-pr-reviewer
Warn
Audited by Snyk on Jul 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). At runtime the skill uses
gh pr view/gh pr diff, which ingest outsider-authored GitHub PR body text and diff content (including comments/changes written by non-operating users) into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata