The Agent Skills Directory

[Unverifiable Dependencies] (LOW): The skill instructs the user to connect to a third-party MCP server hosted at https://rube.app/mcp. This domain is not part of the trusted organizations list, making it an unverified external dependency.
[Indirect Prompt Injection] (LOW): The skill defines a workflow that ingests untrusted data from an external source (Airtable), which could contain malicious instructions designed to manipulate the agent's behavior.
Ingestion points: Data is ingested via AIRTABLE_LIST_RECORDS, AIRTABLE_GET_RECORD, and AIRTABLE_LIST_COMMENTS from the SKILL.md file.
Boundary markers: Absent. The skill provides no instructions or delimiters to help the agent distinguish between data and instructions within the records.
Capability inventory: The skill provides full CRUD capabilities on Airtable bases via AIRTABLE_CREATE_RECORD, AIRTABLE_UPDATE_RECORD, and AIRTABLE_DELETE_RECORD as seen in SKILL.md.
Sanitization: Absent. There is no evidence of sanitization or validation of the content retrieved from Airtable before it is processed by the agent.

airtable-automation