copywriting

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured instructions and templates for copywriting tasks, focusing on conversion-oriented writing principles.
  • [DATA_EXPOSURE]: The skill reads from .claude/product-marketing-context.md to gather project-specific context. This is a standard practice for tailoring AI responses to a specific workspace and does not involve exfiltration of sensitive system credentials or private keys.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface through the processing of user-supplied marketing context and the .claude/product-marketing-context.md file.
  • Ingestion points: .claude/product-marketing-context.md, User prompt input.
  • Boundary markers: None explicitly defined for the external file content.
  • Capability inventory: File reading (internal context), text generation.
  • Sanitization: Includes a 'Quick Quality Check' and 'Writing Style Rules' that enforce output constraints, reducing the likelihood of executing instructions hidden within the source data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 06:05 AM
Security Audit — agent-trust-hub — copywriting