skills/svenja-dev/claude-code-skills/auto-pr-pipeline/Snyk

auto-pr-pipeline

Warn

Audited by Snyk on Mar 28, 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 reads repository and GitHub metadata (e.g., "open threads / requested changes", PR comments, Review-Entscheidung, and .github workflows) via repo-file and GitHub-API/gh detection, so it ingests untrusted, user-generated third-party content (PR comments/reviews) that can directly influence decisions and tool actions.

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Mar 28, 2026, 02:26 AM

Issues

1