prompt-engineering-library
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were found in the skill content. The skill purely generates text templates for marketing purposes.
- [PROMPT_INJECTION]: The skill incorporates defensive instructions, such as using triple hash marks (###) to separate system instructions from user-provided content (e.g., client briefs or comments). This is a documented mitigation technique to prevent the AI from confusing data with instructions.
- [DATA_EXFILTRATION]: The templates include placeholders for WhatsApp links (wa.me), which are standard for the intended marketing use case in the target region. No automated network requests or exfiltration patterns were identified.
Audit Metadata