yt-comment
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from YouTube comments and transcripts to draft replies and maintain a local voice profile file.
- Ingestion points: Comment threads and video transcripts provided by the user (referenced in SKILL.md).
- Boundary markers: Absent. There are no instructions to the agent to treat external content as data only or to ignore embedded commands.
- Capability inventory: The skill uses the agent's capabilities to read and write to the local file system (~/.claude/youtube/voice.md).
- Sanitization: Absent. No validation, filtering, or escaping is performed on the ingested YouTube content before it is processed or saved to the persona file.
Audit Metadata