btl-messaging

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install and run a Node.js package using npx -y @coldiq/mcp@latest. This package is the official tool provided by the skill author (Cold-IQ) to enable the required functionality.
  • [COMMAND_EXECUTION]: The skill provides a command-line instruction COLDIQ_API_KEY=<key> npx -y @coldiq/mcp@latest for users to set up the necessary environment. This is a standard procedure for integrating vendor-provided tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted data from external sources.
  • Ingestion points: Data is fetched via mcp__coldiq__extract_post_engagement (public posts) and mcp__coldiq__fetch_page_content (external web pages).
  • Boundary markers: None identified in the prompt interpolation instructions.
  • Capability inventory: The skill uses network-enabled MCP tools to find signals and verify emails.
  • Sanitization: There are no explicit instructions to sanitize or escape the content fetched from external sources before using it to draft emails.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 06:37 PM
Security Audit — agent-trust-hub — btl-messaging