yt-audit
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts located in sibling directories:
../yt-package/title.pyand../yt-script/hookscore.py. It also reads personal stylistic data from the path~/.codex/youtube/voice.mdto establish a user voice profile for the audit report. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from YouTube video titles and transcripts, which could be exploited to deliver malicious instructions to the agent.
- Ingestion points: YouTube video titles and transcripts for the first fifteen seconds of videos (SKILL.md).
- Boundary markers: Absent. The instructions do not provide delimiters or warnings to treat external content as non-executable data.
- Capability inventory: The agent can execute scripts in adjacent directories and read local files from the user's home directory.
- Sanitization: No evidence of sanitization, filtering, or validation is present for the ingested external metadata or transcriptions.
Audit Metadata