fourth
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from the Fourth HRIS platform (e.g., employee records, time-off requests), which constitutes an untrusted data source.
- Ingestion points: Data is retrieved via
apideck.hris.employees.list()and other HRIS unified API methods described inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or specific instructions to the agent to ignore embedded commands within the retrieved HRIS data.
- Capability inventory: The skill uses the
@apideck/unifySDK and rawcurlcommands via a Proxy API to interact with external services. - Sanitization: There is no mention of sanitizing or filtering the content retrieved from the Fourth API before it is processed by the agent.
Audit Metadata