The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill describes tools that ingest data from external sources, such as n8n templates and existing workflows, which could theoretically contain malicious instructions. However, this is inherent to the skill's purpose of workflow automation and is documented with standard validation procedures.
Ingestion points: The tools search_templates, get_template, and n8n_get_workflow (referenced in SKILL.md and SEARCH_GUIDE.md) allow the agent to fetch external data into its context.
Boundary markers: No explicit instruction delimiters are suggested for handling these external inputs, though the guide emphasizes rigorous validation using the runtime profile.
Capability inventory: The skill provides documentation for performing write operations via n8n_create_workflow and n8n_update_partial_workflow based on the ingested content.
Sanitization: An auto-sanitization system is described in VALIDATION_GUIDE.md, which automatically corrects structural configuration errors (such as operator metadata) but does not filter natural language instructions.
[EXTERNAL_DOWNLOADS]: The skill documentation references external resources from n8n and the author's official website (aiadvisors.pl). These are standard informational links for a documentation-focused skill and do not involve the execution of untrusted remote code.
[COMMAND_EXECUTION]: While the skill documents tools that interact with a workflow engine, it does not instruct the agent to execute arbitrary shell commands or access sensitive system files. Operations are scoped to the n8n API environment.

n8n-mcp-tools-expert