airtable-automation
Warn
Audited by Snyk on Feb 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's required workflows (Core Workflows in SKILL.md) call toolkit actions like AIRTABLE_LIST_RECORDS, AIRTABLE_GET_RECORD and AIRTABLE_LIST_COMMENTS which ingest arbitrary Airtable record/comment content (user-generated third-party data) that the agent reads and can directly influence subsequent tool actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill requires adding the MCP endpoint https://rube.app/mcp and calls RUBE_SEARCH_TOOLS/RUBE_MANAGE_CONNECTIONS at runtime to fetch tool schemas from that server, which directly determine available tools/instructions the agent will follow, so this external URL controls agent behavior.
Audit Metadata