copywriting
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a standard copywriting assistant that relies entirely on text generation within the agent's safe environment. It does not perform any network operations, execute system commands, or download external dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted user data and context files.
- Ingestion points: User-provided copy descriptions, product details, and the .agents/product-marketing-context.md file.
- Boundary markers: None identified in the instructions to separate data from instructions.
- Capability inventory: None; the skill is limited to text output and lacks network, file-write, or execution capabilities.
- Sanitization: No input validation or sanitization logic is implemented.
- Result: Due to the lack of exploitable capabilities, this surface poses no significant risk.
Audit Metadata