9router-tts
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation provides several curl commands for discovery and usage, enabling the agent to list models, retrieve metadata, and generate speech audio.
- [EXTERNAL_DOWNLOADS]: The skill refers to setup instructions hosted on the author's official GitHub repository (decolua/9router).
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text through the input field to generate audio, creating a potential surface for indirect prompt injection. * Ingestion points: The input parameter in the /v1/audio/speech POST request within SKILL.md. * Boundary markers: No delimiters or ignore instructions are specified for the input data. * Capability inventory: The skill performs network requests via curl and fetch, and includes logic for writing audio data to the local file system. * Sanitization: There is no evidence of input validation or text sanitization before processing.
Audit Metadata