copywriting
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOW
Full Analysis
- Data Exposure & Exfiltration (SAFE): The skill instructions include reading a project-specific marketing context file (
.claude/product-marketing-context.md). No access to sensitive system directories or credentials was identified. - Indirect Prompt Injection (INFO): The skill is designed to process external context data. 1. Ingestion points: File
.claude/product-marketing-context.md. 2. Boundary markers: Absent. 3. Capability inventory: Limited to text generation; no side-effect capabilities (file-write, network, exec) are present in the provided scripts. 4. Sanitization: Absent. - Unverifiable Dependencies & Remote Code Execution (SAFE): No external dependencies, package installations, or remote execution patterns were found.
Audit Metadata