melotts
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied text to perform voice synthesis via the MeloTTS API, which introduces an indirect injection vector.
- Ingestion points: The
textparameter in the API request body sourced from user prompts. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill.
- Capability inventory: Network operations via
curl,requests, andfetch; file system access for writing and reading the API key file. - Sanitization: No sanitization or validation of the input text is implemented.
- [COMMAND_EXECUTION]: The skill instructs the agent to use
chmod 600on the local~/.pixazo/api-keyfile to protect the user's credentials, aligning with security best practices. - [EXTERNAL_DOWNLOADS]: The agent is directed to fetch technical documentation from a vendor-controlled URL (
https://www.pixazo.ai/models/melotts.md) to resolve model-specific parameters.
Audit Metadata