write-judge-prompt
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No security issues detected. The skill is composed entirely of Markdown documentation and YAML configuration files providing a framework for designing LLM-as-Judge evaluators.
- [NO_CODE]: The skill does not include or reference any scripts, binaries, or command-line execution patterns. It functions as a set of guidelines for the AI agent to assist users in prompt design.
- [INDIRECT_PROMPT_INJECTION]: While the skill instructs the agent to process user-provided failure modes and examples to generate prompts, it has no capabilities (e.g., file writing, network access, or command execution) to exploit. The risk is negligible as it remains within the conversational context.
Audit Metadata