skills/kfchou/wiki-skills/wiki-audit/Gen Agent Trust Hub

wiki-audit

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a verification workflow for markdown documents. It reads local files (SCHEMA.md, wiki/pages/), checks citations, and uses a subagent pattern to verify text against source PDFs or text files. The 'strong mode' involves a secondary model call to detect logical overreach or contradictions. No malicious patterns such as data exfiltration, obfuscation, or unauthorized network operations were detected. External URL handling is limited to checking for cached copies or asking the user to re-fetch, which is standard behavior for the described tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:42 PM
Security Audit — agent-trust-hub — wiki-audit