inbound-triggers-30

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to execute npx -y @coldiq/mcp@latest. This command downloads and runs the official Model Context Protocol server from the skill's author (Cold-IQ) via the npm registry to enable intent detection and web search capabilities.- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it utilizes tools designed to ingest untrusted data from external sources.
  • Ingestion points: External data is ingested through the mcp__coldiq__find_signals and mcp__coldiq__search_web tools referenced in SKILL.md.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the skill's instructions.
  • Capability inventory: The skill uses tools for email discovery and verification (mcp__coldiq__find_emails, mcp__coldiq__verify_email) based on the ingested signals.
  • Sanitization: There are no documented sanitization or validation steps for the content retrieved from external signals or web searches.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 06:37 PM
Security Audit — agent-trust-hub — inbound-triggers-30