copy-editing
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user-supplied marketing copy, creating a surface for indirect prompt injection attacks.
- Ingestion points: Marketing copy provided by the user for review or editing as described in SKILL.md.
- Boundary markers: The instructions lack delimiters or specific warnings to ignore potentially malicious commands embedded in the text being edited.
- Capability inventory: The skill is designed to read local environment context files such as .agents/product-marketing.md.
- Sanitization: No input validation or filtering logic is specified for the user-supplied content.
Audit Metadata