payabli-disputes
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill interacts with external data by querying chargeback records via
GET /Query/chargebacksand submitting evidence viaPOST /ChargeBacks/response/{Id}. This data ingestion from potentially untrusted external sources (e.g., customer communication or transaction metadata) creates a surface for indirect prompt injection. Ingestion points: API responses from chargeback queries. Boundary markers: None specified for the processed data. Capability inventory: Network requests to Payabli API endpoints and reading the local configuration filepayabli-integration.md. Sanitization: No explicit sanitization or validation of external content is mentioned. - [SAFE]: All external references point to official documentation at
docs.payabli.com, which is the authorized domain for the vendor 'payabli'. - [SAFE]: The instructions to read
payabli-integration.mdto determine SDK configuration is a routine integration practice and does not involve accessing sensitive system files or credentials.
Audit Metadata