sentry-code-review
Warn
Audited by Snyk on Feb 17, 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 GitHub pull request review comments (via the gh API or WebFetch) and parses the comment bodies—including the "🤖 Prompt for AI Agent" section—so it ingests untrusted, user-generated third-party content from public PRs.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill fetches PR review comments at runtime from GitHub (e.g., https://api.github.com/repos/{owner}/{repo}/pulls/<PR_NUMBER>/comments or the PR URL) and parses the comments' "🤖 Prompt for AI Agent" section, which directly supplies instructions that will control the agent.
Audit Metadata