hr-works
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of data from the HR Works platform, which acts as an external ingestion point for potentially untrusted content. Malicious data within these records could attempt to influence agent behavior.\n
- Ingestion points: Employee, department, payroll, and time-off records fetched from the HRIS API.\n
- Boundary markers: Not present; the instructions do not specify delimiters to separate external data from system prompts.\n
- Capability inventory: Provides read and write access to HR records via the Apideck unified API.\n
- Sanitization: No sanitization or validation logic is defined for the content of the retrieved records.\n- [EXTERNAL_DOWNLOADS]: Fetches API configuration files from the developer's official domain.\n
- Evidence: References https://specs.apideck.com/hris.yml for the OpenAPI specification.\n- [COMMAND_EXECUTION]: Provides template curl commands for checking connector coverage and using the Proxy API.\n
- Evidence: Example commands targeting https://unify.apideck.com/ in SKILL.md.
Audit Metadata