kryptogo-pay-webhook
Fail
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: CRITICALINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of a webhook endpoint that ingests external, untrusted JSON payloads from a payment provider. While the provided code snippets follow standard development practices, the ingestion of external data that might be later processed by an AI agent creates a potential attack surface for indirect prompt injection if the payload contains malicious instructions.
- Ingestion points: Webhook endpoint request bodies (
req.bodyorrequest.json) as defined inreferences/code-examples.mdand described inSKILL.md. - Boundary markers: None present in the provided code snippets to delimit untrusted data or warn downstream systems about embedded instructions.
- Capability inventory: The generated code performs database updates (
order.update,db.session.commit) and triggers user notifications (notifyUser). - Sanitization: The implementation relies on standard framework/ORM behaviors (Express, FastAPI, Flask, NestJS) which provide basic protection against common injection attacks but do not specifically filter for natural language prompt injection content.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
Audit Metadata