security-guardian

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a set of operational protocols for project management, testing, and cognitive integrity. No malicious instructions, obfuscation, or unauthorized access patterns were detected.
  • [SAFE]: The 'GLOBAL PROTOCOLS' explicitly include security best practices, such as treating web content as hostile and redacting secrets or PII before sharing context.
  • [SAFE]: The skill mentions local file system discovery (e.g., docs/graph.json, package.json) and the use of testing tools (rtk npm test) which are standard activities for a development-oriented agent. No sensitive system paths or network exfiltration patterns are present.
  • [SAFE]: The skill is a compatibility shim intended to route legacy prompts to modern runtime capabilities, which is a benign maintenance function.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 07:35 AM
Security Audit — agent-trust-hub — security-guardian