Skills
skills/quinteroac/comfy-agent-tools/comfy-media/Gen Agent Trust Hub

comfy-media

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses uv run to execute local commands for indexing media files and starting a local gallery server.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx hyperframes to preview exported projects, which involves fetching and executing a package from the npm registry.
  • [SAFE]: The gallery server is explicitly configured to bind to 127.0.0.1 (localhost), preventing unauthorized remote access to generated media.
  • [SAFE]: The documentation includes security-conscious instructions, advising against public exposure and explicitly stating that manifests exclude sensitive data like API keys.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 02:33 AM
Security Audit — agent-trust-hub — comfy-media