youtube-skill

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection via the ingestion of untrusted external content.
  • Ingestion points: The comments command in youtube_skill.py retrieves untrusted text directly from YouTube comment threads.
  • Boundary markers: The script does not utilize delimiters or specific instructions for the agent to ignore or isolate instructions embedded within the retrieved comment data.
  • Capability inventory: The skill includes high-impact write capabilities, such as upload, comment, reply, subscribe, and create-playlist in youtube_skill.py, which could be exploited if an injection is successful.
  • Sanitization: Comment text is processed and returned to the agent without any sanitization, filtering, or validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 03:20 PM