copywriting
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input regarding product offers and audience demographics to generate copy.
- Ingestion points: User provides product/audience context in response to prompts (SKILL.md).
- Boundary markers: No explicit boundary markers or 'ignore' instructions for the ingested data are present.
- Capability inventory: The skill contains no code execution, file system access, or network operations.
- Sanitization: No input sanitization or filtering is performed on the user-provided context.
- [SAFE]: The skill follows standard instructional patterns for text generation tasks without any evidence of obfuscation, exfiltration, or unauthorized command execution.
Audit Metadata