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

topaz

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches model configuration and additional instructions from the vendor's official domain at https://www.pixazo.ai/models/topaz.md to ensure accurate parameter handling.
  • [DATA_EXFILTRATION]: Manages vendor-specific API credentials by reading from and writing to ~/.pixazo/api-key. It correctly instructs the agent to set restrictive file permissions (chmod 600) for security.
  • [COMMAND_EXECUTION]: Includes implementation examples using curl and provides instructions for managing related tools via npx, all targeting the vendor's official infrastructure.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface by instructing the agent to fetch remote content.
  • Ingestion points: https://www.pixazo.ai/models/topaz.md (referenced in SKILL.md)
  • Boundary markers: Absent
  • Capability inventory: File system access (~/.pixazo/api-key), network operations (Python requests, Node.js fetch, shell curl)
  • Sanitization: Absent
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 11:17 AM