pr-feedback-classifier

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: 0.80). The SKILL.md explicitly instructs the agent to call "erk exec get-pr-feedback" to fetch PR review_threads and discussion_comments (user-generated PR comments) and to classify them and drive batching/auto-resolve decisions, so untrusted third-party PR content is read and can materially influence tool actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 03:05 PM