youtube-research-video-topic

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill demonstrates a surface for indirect prompt injection by processing external YouTube metadata and web content. Evidence Chain: 1. Ingestion points: youtube-analytics search tools and web-fetch. 2. Boundary markers: Absent. 3. Capability inventory: Filesystem writing and subagent tasking via the Task tool. 4. Sanitization: Absent. This risk is inherent to the research task and is considered a low-severity surface associated with the primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:12 PM