payabli-accept-payments
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read a file named
payabli-integration.mdfrom the repository root and to "honor" its content regarding SDK preferences and integration scope. This mechanism allows external, untrusted data in the project environment to influence the agent's behavior and code generation. - Ingestion points: The agent is directed to read
payabli-integration.mdat the root of the repository. - Boundary markers: Absent; the skill does not specify any delimiters or instructions to ignore potential commands embedded within the configuration file.
- Capability inventory: The agent is tasked with generating code for financial operations, including processing payments, managing customer data, and handling refunds via the Payabli API.
- Sanitization: No validation or sanitization steps are defined for the content read from the external file.
Audit Metadata