skills/pixazo-ai/skills/chatterbox/Gen Agent Trust Hub

chatterbox

Pass

Audited by Gen Agent Trust Hub on Oct 17, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill manages a vendor-specific API key stored in ~/.pixazo/api-key. It correctly instructs the agent to set restrictive file permissions (chmod 600) to protect the credential.
  • [EXTERNAL_DOWNLOADS]: The skill references and fetches documentation and configuration from the vendor's official domain (pixazo.ai) and gateway (gateway.pixazo.ai). These are legitimate vendor resources used for the skill's primary functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text and audio URLs from the user to process them via the TTS API. While this creates a potential surface for indirect prompt injection, the data is passed to a specific vendor endpoint for processing, and no unsafe interpolation into system instructions was detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 17, 2026, 07:56 AM