brand-copy
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a set of natural language prompts for a brand copywriter persona and does not include any executable scripts or configuration for external tools.
- [NO_CODE]: No code files or external packages are referenced or included.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it processes untrusted user input (product and audience information) to generate marketing materials. 1. Ingestion points: Workflow section (product and audience details). 2. Boundary markers: Absent. 3. Capability inventory: The skill is restricted to generating text responses and does not have access to shell commands, network operations, or file system modifications. 4. Sanitization: Absent. Given the lack of dangerous capabilities, the presence of an ingestion surface does not pose a security risk.
Audit Metadata