title-formulas

Pass

Audited by Gen Agent Trust Hub on Nov 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data fetched from YouTube (video titles, channel names, and descriptions) via the required TubeLab MCP.
  • Ingestion points: External video data enters the agent context through search results and outlier analysis (SKILL.md).
  • Boundary markers: The output uses structured markdown (headers, tables, and code blocks) to organize data, though it lacks explicit instructions to ignore instructions that might be embedded in video titles.
  • Capability inventory: The skill interacts with the TubeLab MCP for data retrieval but does not demonstrate capabilities for file system modification, network exfiltration, or arbitrary command execution.
  • Sanitization: No specific sanitization or filtering of the ingested title strings is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 21, 2026, 04:16 PM