copywriting
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill consists of markdown instructions and reference guides for writing marketing copy. It utilizes local context files (MEMORY.md and USER.md) to tailor its output to the user's specific company and preferences, which is standard practice for AI agent personalization.
- [PROMPT_INJECTION]: The skill ingests user-provided descriptions of products, audiences, and pages. While this constitutes an indirect prompt injection surface, the risk is negligible as the skill lacks high-privilege capabilities such as shell execution, network operations, or arbitrary file writing.
- Ingestion points: User-provided context regarding page purpose, audience demographics, and product value propositions in SKILL.md.
- Boundary markers: None present.
- Capability inventory: The skill does not use or request any subprocess, network, or file-write capabilities.
- Sanitization: No input sanitization or filtering is defined.
Audit Metadata