airtable

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime path uses curl to call Airtable’s REST API with the user’s PAT and then pretty-prints the JSON response; Airtable record/table content is outsider-authored free text (other users’ Airtable data) that can be ingested into the agent’s LLM context via the tool output.