workday
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the retrieval of data from external Workday environments (Accounting, HRIS, and ATS records). This creates a potential surface for indirect prompt injection if the retrieved data (such as invoice notes or applicant details) contains instructions designed to influence the agent's behavior.
- Ingestion points: API responses from Workday resources accessed through the
@apideck/unifySDK mentioned inSKILL.md. - Boundary markers: No specific delimiters or "ignore instructions" warnings are included in the example code snippets.
- Capability inventory: The skill enables reading, writing, and reconciling records via authenticated API calls.
- Sanitization: No explicit sanitization or validation logic is defined within the skill's instructions.
- [EXTERNAL_DOWNLOADS]: The skill references official vendor resources, including OpenAPI specifications from
specs.apideck.comand documentation fromdevelopers.apideck.comandworkday.com. These are legitimate, non-malicious references to the service provider's infrastructure.
Audit Metadata