skills/devskale/skale-skills/youtube/Gen Agent Trust Hub

youtube

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill instructions or the Python script.
  • [EXTERNAL_DOWNLOADS]: The skill connects to https://yt.tarka.dev to retrieve video metadata. This is a well-known public Invidious instance used for privacy-respecting YouTube searches and does not involve downloading executable code.
  • [COMMAND_EXECUTION]: The skill relies on its own local script search.py. There are no instances of spawning arbitrary shell commands, subprocesses, or elevated privileges.
  • [DATA_EXFILTRATION]: No sensitive local information is accessed. The only data transmitted is the search query provided by the user to the API.
  • [PROMPT_INJECTION]: The instructions do not contain any attempts to bypass model safety filters or override system instructions.
  • [DYNAMIC_EXECUTION]: The script uses json.loads() to process API data, which is a safe method for parsing structured data compared to dangerous alternatives like eval() or pickle.loads().
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 02:42 AM