manage-pull-requests
Warn
Audited by Snyk on Jun 15, 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 reads PR discussion by calling
harness_list(resource_type="pr_activity", kind="comment"), which returns outsider-authored free-text comments (e.g., other users’ review comments) that are then ingested into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata