yt-audit

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes untrusted YouTube content.
  • Ingestion points: YouTube channel pages, titles, and video transcripts (SKILL.md).
  • Boundary markers: No delimiters or ignore instructions are defined for external data.
  • Capability inventory: Analysis and text generation for audit reports.
  • Sanitization: No data sanitization is performed on ingested content.
  • Note: The risk is mitigated by a mandatory human-in-the-loop confirmation step.
  • [COMMAND_EXECUTION]: The skill directs the agent to execute a title linter script from a related skill directory, which is a standard part of its modular design.
  • [SAFE]: No malicious patterns or critical security vulnerabilities were detected. The skill includes a 'gate' requiring user confirmation before any final action is taken and accesses local configuration for user preferences.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 05:52 AM