airtable

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). This skill explicitly instructs the agent to fetch and act on Airtable data via Membrane (e.g., "list-records", "get-record", "list-bases" and the "membrane request" proxy in SKILL.md), which can contain untrusted user-generated content that the agent will read and that could materially influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:55 AM