steelman-both-sides

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains strict behavioral instructions to ensure the AI follows a specific reasoning process. These instructions are functional for the intended use case and do not target safety guardrails or attempt to leak system instructions.
  • [SAFE]: No external downloads, remote code execution, or credential exposure were found. The skill documentation mentions a sync script for repository maintenance, but this is not an executable component of the agent's runtime environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 06:05 PM
Security Audit — agent-trust-hub — steelman-both-sides