perf-theory-tester

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE] (SAFE): No malicious instructions, prompt injections, or data exfiltration patterns were detected in the skill definition.
  • [NO_CODE] (SAFE): The skill consists exclusively of markdown instructions without any bundled scripts, binaries, or automated installation steps.
  • [COMMAND_EXECUTION] (LOW): The skill instructions involve running benchmark commands and modifying files. While these are high-privilege operations, they are explicitly tied to the primary purpose of performance testing and are presented as part of a controlled experimental workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 02:07 AM