The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data including invoice references, descriptions, and vendor metadata, which could be used to influence agent behavior if not properly handled.
Ingestion points: Data is ingested through getScheduledPayments in the recurring bills workflow and via the processContractorPayment function arguments in SKILL.md.
Boundary markers: The instructions do not explicitly define delimiters or boundary markers for untrusted data when it is interpolated into internal logic or logs.
Capability inventory: The agent possesses high-impact capabilities including payments.send for executing financial transfers, logPayment, and notifyRequester.
Sanitization: No explicit sanitization or strict schema validation for the memo or description fields is demonstrated in the provided logic snippets.

Accounts Payable Agent