meta-prompting

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill is a text-only prompt engineering tool composed entirely of markdown instructions. It does not include any scripts, binaries, or automated installation processes.
  • [SAFE]: No malicious patterns, such as data exfiltration, hardcoded credentials, or obfuscated code, were detected. The slash commands are designed to improve logical analysis and structured outputs within the existing agent conversation.
  • [PROMPT_INJECTION]: The skill includes instructions to override specific formatting constraints (e.g., sentence counts) and allows users to define new patterns mid-conversation. These are functional features of the reasoning logic and do not instruct the AI to bypass core safety protocols or ignore system instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 05:51 PM