pr-merge
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill fetches and reads GitHub pull request data (titles, descriptions, files, reviews, diffs) from user-generated public repositories via MCP GitHub endpoints, exposing the agent to untrusted third-party content that could carry indirect prompt injections.
Audit Metadata