airtable

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

• Third-party content exposure detected (high risk: 0.70). The skill directly fetches and reads user-generated Airtable content (see the "List Records" and "List Record Comments" API calls to https://api.airtable.com/v0/... in SKILL.md), which the agent is expected to interpret as part of its workflow and could influence subsequent create/update/delete actions—exposing it to untrusted third-party content that could carry indirect prompt injection.