n8n-marketing-flows
Warn
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs the agent to clone an external GitHub repository (
https://github.com/YuriCrystal/n8n-marketing-flows.git) containing automation templates that are then imported and executed within the n8n environment. These templates are not from a verified or trusted vendor. - [INDIRECT_PROMPT_INJECTION]: The skill sets up automation flows that ingest data from external, untrusted sources such as RSS feeds (TechCrunch, Hacker News) and forum posts (PTT) and passes this content directly into LLM prompts.
- Ingestion points: RSS Read nodes and HTTP Request nodes targeting public forums.
- Boundary markers: Absent; the provided prompt templates do not include instructions for the LLM to ignore embedded commands or malicious instructions within the fetched data.
- Capability inventory: The skill has the capability to perform network requests (HTTP Request nodes), send notifications to external services (Slack, Discord, Email), and execute code (Code nodes).
- Sanitization: Absent; external content is interpolated directly into prompts using template variables like
{{ $json.postText }}and{{ $json.content }}without validation or filtering. - [COMMAND_EXECUTION]: The installation instructions include commands for global package installation (
npm install -g n8n) and Docker execution with local filesystem mounting (-v ~/.n8n:/home/node/.n8n), which grants the container access to the user's home directory.
Audit Metadata