copywriting
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured guidance for copywriting based on industry-standard frameworks such as the Human Action Model and various headline formulas.
- [SAFE]: The skill is designed to read context from specific local files like .agents/product-marketing.md to ensure brand consistency. This is a standard functional feature for contextual AI agents.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information and reads local project files to generate copy. 1. Ingestion points: User input prompts and local markdown files (.agents/product-marketing.md, etc.) as defined in SKILL.md. 2. Boundary markers: The instructions do not define specific delimiters for separating processed data from the system prompt. 3. Capability inventory: The skill is limited to text generation and does not perform file writes, network operations, or shell command executions. 4. Sanitization: No explicit sanitization or validation of the input content is performed before processing.
Audit Metadata