copywriter-pro
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted user input to generate marketing copy.
- Ingestion points: User-provided context fields including 'Product / Service', 'Target persona', and 'Core pain point' in
SKILL.mdandtemplates/prompt-main.md. - Boundary markers: The skill does not employ specific delimiters or 'ignore embedded instructions' warnings for interpolated user data.
- Capability inventory: The skill is limited to text generation and does not utilize subprocesses, file writes (beyond standard agent output), or network operations.
- Sanitization: No input validation or sanitization mechanisms are present to filter potential instructions hidden within the user-provided product details.
Audit Metadata