consult-tavernweave-library

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a knowledge repository containing reference material for SillyTavern character card formats, regex mechanisms, and UI/UX design patterns. No malicious code or instructions were detected.
  • [SAFE]: The documentation includes security-focused chapters (e.g., D6 on XSS protection) that provide purely defensive and educational guidance for developers.
  • [SAFE]: The execution instructions in SKILL.md are standard tool-use patterns, directing the agent to run a local script for routing documentation based on the user's intent. No confirmable remote code execution or suspicious network patterns were identified.
  • [SAFE]: The assets provided, including a web-based 'picker' tool and several HTML previews of web APIs (e.g., Wasm, CSS, WebGPU), are designed for local offline browsing and demonstration purposes and do not exhibit malicious behavior.
  • [SAFE]: Data integrity is maintained via a manifest containing file hashes, and the instructions specifically forbid the agent from leaking internal driver or inbox material.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 08:37 AM
Security Audit — agent-trust-hub — consult-tavernweave-library