prompt-engineering-system-prompt
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [PROMPT_INJECTION]: The analysis identified keywords such as 'ignore previous instructions'; however, these are used strictly in an educational context. The file describes how to write rules that resist injection and provides a testing checklist to ensure defenses are working. It does not attempt to subvert the agent's behavior.\n- [METADATA_POISONING]: Metadata fields are descriptive and consistent with the provided documentation. The author information and cross-references to related prompt engineering skills appear legitimate and functional.\n- [NO_CODE]: The skill consists exclusively of markdown documentation. It does not invoke scripts, request remote resources, or perform any automated file or network operations.
Audit Metadata