timeout-prevention
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: 0.90). This skill includes patterns that fetch and process arbitrary public URLs and user-generated content (e.g., "Pattern 3: Progress-Tracked Downloads" uses yt-dlp on urls.txt/URL, and "Pattern 2: Repository Cloning with Checkpoints" runs git clone on repos from repos.txt), so the agent would ingest untrusted third-party content as part of its workflow, enabling indirect prompt injection risk.
Audit Metadata