audit-channel-risk

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external sources which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: YouTube channel 'About' text, video titles, descriptions, and transcripts (Steps 2 and 3), as well as a live YouTube policy page or a user-provided 'paste' of the policy (Step 1).
  • Boundary markers: The instructions do not define boundary markers or 'ignore' instructions for the external content being analyzed.
  • Capability inventory: The skill is capable of generating and saving an HTML file (channel-risk-{handle}.html) and interacting with the TubeLab MCP tools.
  • Sanitization: No sanitization or validation of the ingested external content is specified before it is processed or included in the HTML report.
  • [EXTERNAL_DOWNLOADS]: The skill references and fetches thumbnail images from a remote CDN (https://cdn.tubelab.net/vi/<id>.jpeg). This domain is a vendor-owned resource associated with the author ('tubelabhq').
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 04:24 AM