taruvi-functions

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs creating/proxying functions that call or forward to external webhook URLs and process incoming webhook payloads (see references/modes-and-triggers.md PROXY webhook_url example and references/scenarios.md Scenario 5: external API call and Scenario 7: public webhook receiver), so the agent is expected to ingest and act on untrusted third‑party content and responses.