copywriting
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a set of instructional guidelines and reference materials for copywriting and editing. It does not contain any executable code, network operations, or sensitive file access patterns. It utilizes local context files for project-specific information, which is a standard and safe platform feature.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided copy for editing purposes, creating a surface for indirect prompt injection.
- Ingestion points: User-provided marketing copy for editing (SKILL.md).
- Boundary markers: Not explicitly defined in the prompt instructions.
- Capability inventory: The skill is restricted to text generation and modification; no subprocess calls, network operations, or file-write capabilities were detected across the instruction set or reference files.
- Sanitization: No specific sanitization, filtering, or escaping of input content is implemented.
Audit Metadata