using-gh-cli-search

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • PROMPT_INJECTION (LOW): The skill uses strong imperative language to enforce strict behavioral compliance and tool usage.
  • Evidence: Inclusion of phrases like 'EXTREMELY-IMPORTANT', 'MANDATORY', 'not optional', and 'You cannot rationalize your way out of this'.
  • Risk: This approach attempts to prioritize specific instructions over the agent's general reasoning and safety training, which is a common vector for behavioral manipulation.
  • NO_CODE (SAFE): The analyzed file contains only Markdown text and metadata. No executable code, shell scripts, or external dependencies were detected, minimizing technical risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:43 PM