whisper
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data which could potentially contain malicious instructions.\n
- Ingestion points: User prompts, audio URLs, and reference images provided during the conversation (SKILL.md).\n
- Boundary markers: None present; the skill does not use delimiters to isolate user-provided content.\n
- Capability inventory: File system write access (~/.pixazo/api-key), network requests (gateway.pixazo.ai), and shell command execution (chmod, curl).\n
- Sanitization: None present; user inputs are interpolated directly into API request bodies without validation or escaping.\n- [EXTERNAL_DOWNLOADS]: Fetches additional model documentation and reference schemas from the vendor's official domain (pixazo.ai).\n- [COMMAND_EXECUTION]: Executes shell commands to manage file permissions (chmod 600) and perform network operations (curl) for API interactions.
Audit Metadata