niche-watchlist

Pass

Audited by Gen Agent Trust Hub on Nov 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from YouTube (titles, descriptions, channel handles) to generate reports. This creates a surface where malicious instructions could be embedded in external content to influence the agent.
  • Ingestion points: YouTube search results and channel metadata from the TubeLab MCP are processed during the monitoring and analysis workflow.
  • Boundary markers: No delimiters or 'ignore embedded instructions' warnings are present to prevent the agent from obeying instructions found in video metadata.
  • Capability inventory: The skill is capable of reading, writing, and updating files within the 'watchlist/' local directory.
  • Sanitization: External content is directly interpolated into markdown output templates without escaping or validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 21, 2026, 04:16 PM