address-pr-reviews
Warn
Audited by Snyk on Mar 8, 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 fetches PR review bodies and inline review thread comments from GitHub (see "Fetch Reviews and Threads" GraphQL query for reviews and reviewThreads), which are untrusted, user-generated third-party content that the agent is instructed to read and act on (fix code, post replies, resolve threads), allowing reviewer text to materially influence actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill invokes GitHub CLI/API (e.g., gh api graphql → https://api.github.com/graphql) at runtime to fetch PR review bodies and threads whose content directly drives what the agent does (fixes/replies), and the skill depends on that external content.
Audit Metadata