tada
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches extended documentation and API schemas from the vendor's official website at https://www.pixazo.ai/models/tada.md to assist the agent in selecting correct parameters.
- [COMMAND_EXECUTION]: The documentation references a command for installing related skills from the vendor's repository (Pixazo-AI/skills) using npx.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-supplied text and audio URLs for processing by the TTS API, creating a potential surface for indirect injection.
- Ingestion points: User input fields for 'prompt' and 'audio_url' in SKILL.md.
- Boundary markers: No explicit delimiters or instructions are provided to the agent for separating user data from system instructions.
- Capability inventory: The skill performs outbound HTTP requests via curl, Python, and Node.js.
- Sanitization: No specific input validation or filtering is defined for the user-provided content.
- [SAFE]: The skill implements secure credential management by searching environment variables and a local vendor-specific path (~/.pixazo/api-key). It correctly instructs the agent to apply restrictive file permissions (chmod 600) to protect the stored key.
Audit Metadata