email-writing-frameworks

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to run the @coldiq/mcp package using npx. This package belongs to the skill's author, Cold-IQ.
  • [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface as it retrieves external data from social media and websites to populate email templates.
  • Ingestion points: Data retrieved via mcp__coldiq__extract_post_engagement and mcp__coldiq__fetch_page_content tools.
  • Boundary markers: There are no specific delimiters or instructions to isolate the fetched external data from the surrounding prompt context.
  • Capability inventory: The skill utilizes the agent's ability to call MCP tools to fetch and process data.
  • Sanitization: No evidence of validation or sanitization of the external content before it is used in email generation was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 06:37 PM
Security Audit — agent-trust-hub — email-writing-frameworks