homerun-hr
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as an interface for external HRIS data, which introduces a potential surface for indirect prompt injection if the processed data contains malicious instructions. \n
- Ingestion points: Data retrieved from Homerun HR API endpoints, including employee profiles and payroll records (SKILL.md). \n
- Boundary markers: No specific delimiters or boundary markers are defined in the instructions to isolate external data from the agent's prompt context. \n
- Capability inventory: The skill enables network operations via the
@apideck/unifySDK and curl commands to interact with the Apideck unified API (SKILL.md). \n - Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the data ingested from the external service.
Audit Metadata