expression-skill

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: This skill is entirely instructional. It provides behavioral guidelines for an AI agent to adopt a concise and structured communication style (e.g., 'Conclusion First', 'Concrete Over Abstract'). It does not introduce any functional risk to the environment.
  • [SAFE]: No data exposure or exfiltration patterns were detected. The skill does not access sensitive file paths, environment variables, or hardcoded credentials.
  • [SAFE]: No remote code execution or unverifiable dependencies were found. While examples mention development tools like 'uv' and 'pytest', they are used purely as illustrative content for how a communication report should look.
  • [SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected in the instructions or example files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 09:22 AM
Security Audit — agent-trust-hub — expression-skill