NYC

video-archival-system

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Indirect Prompt Injection] (SAFE): The skill is designed to handle external URLs which is a surface for indirect prompt injection. However, since no implementation code is provided, the risk is negligible. 1. Ingestion points: YouTube and Playlist URLs. 2. Boundary markers: Absent. 3. Capability inventory: No scripts or tools provided. 4. Sanitization: None present.
  • [Code Analysis] (SAFE): No scripts, binaries, or system commands were found in the skill files.
  • [Data Security] (SAFE): No hardcoded credentials or sensitive file paths (like SSH keys or AWS configs) are present; the reference to ~/Downloads/ is a standard user directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:02 PM