The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data from various API providers, which creates a potential surface for instructions embedded in third-party data to influence the agent.
Ingestion points: The skill ingests data from external API responses via fetch calls to Slack, Google Sheets, Jira, GitHub, and other services within the connectivity and operation testing functions in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions for the agent to disregard natural language commands that might be present in the data returned by these external services.
Capability inventory: The skill utilizes network capabilities (fetch) to interact with multiple external platforms.
Sanitization: The provided patterns include basic data validation and classification but do not implement robust sanitization or escaping of external content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill's instructions and code snippets reference official API endpoints for well-known services, including Slack (slack.com), Google Cloud (googleapis.com), SendGrid, Mailchimp, and Airtable, specifically for the purpose of verifying connectivity and testing n8n node integrations.

n8n-integration-testing-patterns