copywriting

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions reference the @coldiq/mcp package for tool integration. This is a vendor-owned resource belonging to Cold-IQ and is appropriate for the skill's functionality.
  • [PROMPT_INJECTION]: Indirect Prompt Injection surface identified. 1. Ingestion points: mcp__coldiq__fetch_page_content and mcp__coldiq__extract_post_engagement as defined in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Text generation and email verification tools. 4. Sanitization: Absent. This surface is necessary for the skill's core purpose of personalizing copy based on external signals and does not represent a malicious intent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 06:37 PM
Security Audit — agent-trust-hub — copywriting