n8n-docs-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content retrieved from the
n8n-docstool to generate answers. - Ingestion points: Document snippets returned by
n8n-docs(action="lookup"),search, andread(SKILL.md). - Boundary markers: The instructions do not specify delimiters or "ignore embedded instructions" warnings for the ingested documentation data.
- Capability inventory: The skill is informational and does not have capabilities for file writing, arbitrary command execution, or non-whitelisted network operations.
- Sanitization: No explicit validation or filtering of the documentation content is performed before processing.
- [SAFE]: The skill contains specific safety instructions for handling credentials, directing users to the UI modal and explicitly stating that the agent should never ask for secrets to be pasted into the chat interface.
Audit Metadata