show-me-your-work

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a utility for maintaining a transparent decision trail in a TSV format.
  • [SAFE]: The logging script scripts/log.sh includes robust input sanitization. The clean() function removes tabs and newlines to preserve the TSV structure and escapes characters that could trigger formula execution in spreadsheet software (=, +, -, @), mitigating CSV/Spreadsheet Injection risks.
  • [SAFE]: The audit guidelines encourage transparency while respecting privacy, specifically instructing the agent to limit transcript access to the current workspace and avoid scanning unrelated project directories.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 10:42 PM
Security Audit — agent-trust-hub — show-me-your-work