yt-plan
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill reads and writes to the path
~/.codex/youtube/voice.mdwithin the user's home directory. This is used to maintain a voice profile profile and does not involve network exfiltration or access to sensitive system credentials. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and transcribes external user-provided videos to infer a voice profile, which represents an indirect prompt injection surface.
- Ingestion points: User-provided video content and transcripts (SKILL.md).
- Boundary markers: None identified.
- Capability inventory: File system read and write access for managing the voice profile file (SKILL.md).
- Sanitization: No explicit sanitization or validation of the ingested transcript content is mentioned.
Audit Metadata