langfuse-webhooks-events

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a workflow that ingests external data from Langfuse webhooks to trigger downstream actions.
  • Ingestion points: The POST request handler in app/api/webhooks/langfuse/route.ts receives JSON payloads from an external Langfuse instance.
  • Boundary markers: While no specific text boundary markers are used for the prompt data, the skill implements a strict trust boundary for the source using HMAC-SHA256 signature verification.
  • Capability inventory: The integration triggers network calls to Slack and GitHub APIs via fetch, manages an asynchronous queue using bullmq, and can trigger GitHub Action workflows.
  • Sanitization: Authenticity is validated via HMAC-SHA256 signature verification using a shared secret, ensuring that only trusted payloads from the Langfuse instance are processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:46 AM
Security Audit — agent-trust-hub — langfuse-webhooks-events