pr-review

Warn

Audited by Snyk on Feb 15, 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 accepts arbitrary GitHub PR URLs and explicitly queries the GitHub GraphQL API to fetch reviewThreads and comments (comments.nodes[].body) from PRs—untrusted, user-generated content that the agent reads and acts on—exposing it to possible indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 10:14 PM