copywriting
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): The skill consists entirely of natural language instructions, tables, and checklists for copywriting. There are no technical triggers for any of the 10 threat categories.
- Indirect Prompt Injection (SAFE): The skill mentions reading a file named 'SITE.md' to calibrate brand voice. While this constitutes an external data ingestion surface, the skill lacks any capabilities (such as command execution, network access, or sensitive file writes) that could be leveraged for an attack even if 'SITE.md' contained malicious instructions.
Audit Metadata