mmk-youtube-transcript
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill is used to retrieve YouTube transcripts via the vendor's 'mmk' CLI tool. No evidence of credential theft, malicious downloads, or persistence mechanisms was found.
- [COMMAND_EXECUTION]: The skill invokes the 'mmk' tool via Bash. The execution environment is appropriately scoped to this specific toolset using the allowed-tools frontmatter configuration.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes untrusted transcript data from YouTube. Ingestion points: command output from mmk youtube transcript (SKILL.md). Boundary markers: Absent. Capability inventory: Bash command execution via the mmk tool (SKILL.md). Sanitization: Not explicitly defined in the instructions.
Audit Metadata