audience-research

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists exclusively of markdown instructions and templates, with no scripts or executable code provided.
  • [SAFE]: No network requests, external downloads, or data exfiltration mechanisms are present.
  • [SAFE]: Access to the local file '.agents/youtube-context.md' is a standard practice for retrieving project-specific context and does not involve sensitive system paths.
  • [SAFE]: Although the skill directs the agent to process untrusted data (YouTube comments), it does not define or utilize any tools with exploitable capabilities, mitigating the risk of indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:40 PM