iterate-pr

Warn

Audited by Snyk on May 12, 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's required workflow explicitly runs scripts (scripts/fetch_pr_feedback.py and scripts/fetch_pr_checks.py) to ingest GitHub pull request review comments and CI log_snippet data (user-generated third-party content) which the agent reads/interprets and uses to decide fixes and post replies (see "Gather Review Feedback", "Check CI Status", and "Handle Feedback" steps in SKILL.md).

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 12, 2026, 01:12 PM
Issues
1