least-astonishment

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions to override system prompts or bypass safety filters were found. The 'Auto-activate' section is a standard trigger for agent skills and does not constitute a malicious override.
  • [Data Exposure & Exfiltration] (SAFE): No code exists to read sensitive files, environment variables, or perform network requests.
  • [Remote Code Execution] (SAFE): There are no commands for downloading or executing remote scripts (e.g., curl | bash).
  • [No Code] (SAFE): The skill is purely informational, providing guidelines for refactoring and API design without shipping any scripts, binaries, or configuration files that execute logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 09:15 PM