plan-critiquer

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: A thorough analysis of the skill instructions and supporting files shows no signs of malicious behavior or security vulnerabilities.
  • [PROMPT_INJECTION]: The skill adopts a specialized persona for the purpose of strategic analysis; this behavior is task-constrained and does not attempt to bypass system safety guidelines or core agent instructions.
  • [DATA_EXFILTRATION]: No network operations or credential-harvesting patterns were identified. The skill interacts only with project-related files and saves its output locally.
  • [COMMAND_EXECUTION]: The skill does not utilize shell access, subprocesses, or dynamic code execution, relying exclusively on safe file-system tools.
  • [CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or access to sensitive system directories were found in the provided files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 05:54 PM
Security Audit — agent-trust-hub — plan-critiquer