copywriting
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to read external content from a local context file and user-provided descriptions.
- Ingestion points:
SKILL.md(via.claude/product-marketing-context.md) and user-provided marketing data. - Boundary markers: Absent. The skill treats the ingested content as trusted context.
- Capability inventory: The skill only generates text output; it lacks command execution, file-writing, or network capabilities.
- Sanitization: Absent. The skill directly incorporates context into its reasoning.
- Risk: Low impact, limited to the content of the generated marketing copy.
- Data Exposure (INFO): The skill identifies and reads a specific project context file.
- Evidence:
SKILL.mdreferences.claude/product-marketing-context.md. - Observation: This file is a standard location for project-specific metadata in specific AI environments and does not constitute unauthorized access to sensitive system files.
Audit Metadata