pr-research
Warn
Audited by Snyk on Feb 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: 0.90). The skill explicitly instructs the agent to fetch and read public, user-generated repository content (e.g., Phase 0's CONTRIBUTING.md discovery and Phase -1/3 use of gh to list issues/PRs and analyze merged PRs and maintainer comments), so it ingests untrusted third-party pages whose text could influence agent decisions and actions.
Audit Metadata