omniroute-tts
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate audio, creating a potential surface for indirect instructions.
- Ingestion points: The
inputfield in the POST request payload inSKILL.md. - Boundary markers: No delimiters or protective instructions are present to isolate user-supplied text within the payload.
- Capability inventory: The skill utilizes
curlfor network requests to external API endpoints. - Sanitization: There is no evidence of input validation, filtering, or sanitization before processing.
- [EXTERNAL_DOWNLOADS]: The documentation includes a link to an external GitHub repository (github.com/diegosouzapw/OmniRoute) for setup instructions. This is an informational reference to a third-party source and not an automated execution vector.
Audit Metadata