skills/ericrisco/rsc-harness/analyze/Gen Agent Trust Hub

analyze

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely within the local workspace, specifically reading from and writing to the 02-DOCS/wiki/ directory. It does not utilize any tools that interact with the network or external services.
  • [SAFE]: The skill instructions emphasize a 'Report only. Resolve nothing' constraint. It explicitly warns against editing the constitution, spec, plan, or tasks, and forbids opening code files to fix issues, which prevents unauthorized file modifications.
  • [SAFE]: No obfuscation, prompt injection patterns, or privilege escalation mechanisms were detected. The skill uses standard markdown and JSON for its output and state management.
  • [SAFE]: The evaluation files (README.md, cases.yaml) define a rigorous testing harness that focuses on intent-based triggering and capability measurement, further reinforcing the skill's defined boundaries and functional safety.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 09:36 PM
Security Audit — agent-trust-hub — analyze