plaid-webhook-handling
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for ingesting and processing external data via webhooks, which is a common attack surface for indirect prompt injection if the payload contains malicious instructions.
- Ingestion points: Webhook endpoint (
/api/plaid-webhook) defined inSKILL.mdreceives POST requests from external sources. - Boundary markers: The skill explicitly includes and prioritizes a signature verification step using Plaid's JWKs and JWT verification to ensure payload authenticity.
- Capability inventory: The provided examples include database queries (
db.items.findUnique) and Plaid API calls (plaidClient.syncTransactions). - Sanitization: The skill demonstrates best practices by implementing SHA-256 body hashing and signature validation to prevent unauthorized or modified data from being processed.
Audit Metadata