youtube-transcribe
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill utilizes standard external utilities like yt-dlp and sed. It recommends the --cookies-from-browser flag to handle restricted videos, which allows the tool to read sensitive session data from the user's browser.
- [PROMPT_INJECTION] (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) because it fetches and processes untrusted text from YouTube transcripts. 1. Ingestion points: YouTube transcript segments extracted via yt-dlp or browser DOM (SKILL.md). 2. Boundary markers: None; there are no instructions for the agent to treat the transcript as untrusted data or to use delimiters. 3. Capability inventory: Subprocess command execution via yt-dlp and sed, and file system write operations (SKILL.md). 4. Sanitization: None; the extracted text is processed as plain text without filtering or validation.
Audit Metadata