ai-eval-plan

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is a set of markdown-based instructions used to help an agent generate evaluation plans for AI features. It does not perform any sensitive operations.
  • [NO_CODE]: No executable scripts, binaries, or configuration files are present in the skill. It operates entirely through prompt instructions.
  • [PROMPT_INJECTION]: No attempts to override system prompts or bypass safety filters were found. The instructions are focused on the stated purpose of creating evaluation metrics and rubrics.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 09:21 AM
Security Audit — agent-trust-hub — ai-eval-plan