The Agent Skills Directory

[SAFE]: The skill provides documentation and examples for using the UKG Pro connector via Apideck. It follows best practices by using environment variables for sensitive credentials like API keys and interacts with the vendor's own infrastructure (apideck.com).
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from UKG Pro (e.g., employee and payroll records), representing a potential indirect prompt injection surface if the source data were to contain malicious instructions.
Ingestion points: Data is retrieved from UKG Pro via apideck.hris.employees.list and related unified API methods in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters defined to isolate external data from the agent's internal reasoning.
Capability inventory: While the skill itself does not perform dangerous operations like shell execution, it is designed for an agent environment that likely possesses such capabilities.
Sanitization: The skill does not describe specific sanitization or filtering logic for the ingested HRIS data.

ukg-pro