agent-listen
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
rawgenaiCLI tool via the author's Homebrew tap (brew install WHQ25/tap/rawgenai).\n- [INDIRECT_PROMPT_INJECTION]: The skill transcribes audio and video files into text, creating a surface for indirect prompt injection attacks.\n - Ingestion points: Transcribed text from audio/video files processed via the
rawgenaiCLI.\n - Boundary markers: None. The skill does not provide instructions to the agent to treat the transcribed output as untrusted content.\n
- Capability inventory: Execution of the
rawgenaiCLI tool.\n - Sanitization: None. The skill lacks explicit sanitization or validation of the transcribed text.
Audit Metadata