cascade-hr
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of employee and payroll data from IRIS Cascade HR, which represents a potential attack surface for indirect prompt injection if external data contains adversarial instructions.
- Ingestion points: External data is fetched via the
@apideck/unifyNode.js library and direct API calls tounify.apideck.com/proxyas described inSKILL.md. - Boundary markers: The skill instructions lack explicit boundary markers or system instructions to delimit and ignore potentially malicious content within the retrieved API payloads.
- Capability inventory: The skill utilizes network capabilities to communicate with Apideck unified APIs and the Unify Proxy service.
- Sanitization: No specific sanitization, filtering, or validation logic is defined to inspect the external data before it is processed by the agent.
Audit Metadata