product-marketing-copywriter
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of markdown documentation and reference materials. It does not include any scripts, external dependencies, or instructions that trigger network or file system operations.
- [INDIRECT_PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it ingests untrusted product data from the user. However, the associated risk is safe due to the agent's lack of dangerous capabilities. 1. Ingestion points: User-supplied product names, brands, features, and customer reviews as described in Step 1 of SKILL.md. 2. Boundary markers: The instructions do not utilize delimiters or specific warnings to ignore embedded instructions in the user data. 3. Capability inventory: The skill has no capabilities beyond text generation; it cannot access the file system, make network requests, or execute shell commands. 4. Sanitization: No sanitization or validation of user-provided content is performed before the AI processes it.
Audit Metadata