n8n-security-testing
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external n8n workflow exports and execution logs, which presents an attack surface for indirect prompt injection where malicious instructions could be embedded in the analyzed data.
- Ingestion points: Data from workflows and logs is ingested by the
scanForExposedCredentialsandscanExecutionLogsfunctions inSKILL.md. - Boundary markers: The skill provides instructions to the agent to scan these external imports for security vulnerabilities.
- Capability inventory: The skill uses
fetch()to test webhook endpoints and internal API calls to retrieve workflow data. - Sanitization: The skill implementation focuses on detection patterns but does not explicitly specify sanitization steps for the ingested JSON data.
- [EXTERNAL_DOWNLOADS]: The skill configuration defines a dependency on the well-known external utility
jq. - Evidence: The tool
jqis listed as a requirement inscripts/validate-config.jsonandevals/n8n-security-testing.yaml.jqis a trusted utility for JSON processing.
Audit Metadata