email-1-variations-7

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user on how to run a setup command (npx -y @coldiq/mcp@latest) to connect a Model Context Protocol server.
  • [EXTERNAL_DOWNLOADS]: The skill references the author's official API marketplace and downloads the @coldiq/mcp package during the suggested setup process.
  • [REMOTE_CODE_EXECUTION]: The setup instructions include the use of npx, which downloads and executes the latest version of the author's MCP tool from the npm registry.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process data from external sources.
  • Ingestion points: Untrusted data enters the context through tools that fetch public social media posts (mcp__coldiq__extract_post_engagement) and web page content (mcp__coldiq__fetch_page_content).
  • Boundary markers: The skill does not define specific delimiters or instructions to treat fetched content as data only.
  • Capability inventory: The skill environment includes tools for network operations and instructions for command-line package execution.
  • Sanitization: There are no explicit instructions to sanitize or validate external content before using it to generate email drafts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 06:37 PM
Security Audit — agent-trust-hub — email-1-variations-7