The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data from Paychex HRIS records, creating a surface for potential indirect prompt injection if the source data contains malicious instructions. * Ingestion points: The skill uses apideck.hris.employees.list and the Apideck Proxy API (SKILL.md) to fetch employee, department, and payroll data. * Boundary markers: The current documentation and examples do not define specific delimiters or instructions to the agent for separating untrusted data from system instructions. * Capability inventory: The skill utilizes network operations via the @apideck/unify SDK and curl to interact with Apideck and Paychex APIs. * Sanitization: There is no evidence of data sanitization or validation logic applied to the external content before it is processed by the agent.

paychex