NYC

hive-mind-advanced

Warn

Audited by Snyk on Feb 16, 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 includes GitHub integration and explicit repository/PR analysis (e.g., "Analyze repo quality" with --objective "owner/repo" and "Review PR #123"), which requires fetching and interpreting user-generated public repository and pull request content from GitHub — an untrusted third-party source that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:35 AM