connect-ai-airtable

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for the agent to ingest data from external Airtable bases, tables, and views.
  • Ingestion points: The agent is instructed to query record tables, the Comments table, and the Information schema (e.g., SELECT * FROM [YourConnection].[Project tracker].[👀 Overview]).
  • Boundary markers: The skill does not provide specific instructions to use delimiters or ignore embedded instructions when reading content from Airtable fields.
  • Capability inventory: The skill provides instructions for SQL SELECT, INSERT, and UPDATE operations, as well as the DownloadAttachment stored procedure.
  • Sanitization: No explicit sanitization or validation rules are provided for handling content retrieved from Airtable before it is processed by the agent. This is considered a standard ingestion surface for the skill's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 02:10 PM
Security Audit — agent-trust-hub — connect-ai-airtable