agentic-humanizer

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to perform standard file system operations and execute a local binary. Specifically, it reads and writes configuration files in ~/.agentic-humanizer/, removes files for reset commands, and executes a local application binary located at /Applications/Slop Or Not.app/Contents/MacOS/slop for text analysis and cleanup. These operations are consistent with the skill's stated purpose of local text processing and preference management.
  • [SAFE]: The skill implements security-conscious practices, such as explicitly instructing the agent to ignore hidden instructions (Category 8 mitigation) and using SHA-256 hashing to verify the integrity of cached voice fingerprints. It also includes a 'false-positive guard' in references/detection-guidance.md to ensure legitimate human writing is not overly edited.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:10 AM
Security Audit — agent-trust-hub — agentic-humanizer