github
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 explicitly fetches and parses GitHub review threads and comment bodies via GraphQL/REST (see the GraphQL queries and gh api calls in pr-comment-analyzer/SKILL.md and references/github_api_reference.md), which are user-generated, potentially untrusted third‑party content that the agent is expected to read and interpret as part of its analysis.
Audit Metadata