n8n-triggers-webhooks

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of untrusted data from external sources via n8n triggers.
  • Ingestion points: Webhook nodes and app event triggers (e.g., Gmail, HubSpot) described in the 'Trigger Selection Guide' in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when handling external payloads.
  • Capability inventory: The skill suggests passing triggered data to the ColdIQ API or MCP tools (mcp__coldiq__call_endpoint) for enrichment.
  • Sanitization: No explicit validation or sanitization steps are provided for the external data before it is processed by subsequent logic or tools.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to download and run the vendor's MCP server.
  • Evidence: npx -y @coldiq/mcp@latest in SKILL.md.
  • [COMMAND_EXECUTION]: The skill recommends the execution of a shell command to initialize the vendor's MCP environment.
  • Evidence: COLDIQ_API_KEY=<key> npx -y @coldiq/mcp@latest in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 08:55 AM
Security Audit — agent-trust-hub — n8n-triggers-webhooks