kenjo
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes employee, department, and time-off data from Kenjo, creating a surface for indirect prompt injection.
- Ingestion points: Kenjo API responses (employees, departments, payrolls, time-off records) accessed via Apideck's unified HRIS API as described in
SKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to the agent to ignore embedded commands within the ingested data.
- Capability inventory: The agent can list, read, and sync HRIS data using the Apideck SDK or Proxy API calls.
- Sanitization: No sanitization, escaping, or validation of the external HRIS content is mentioned in the instructions.
- [EXTERNAL_DOWNLOADS]: The skill references and fetches resources from well-known vendor-controlled domains.
- Fetches the HRIS OpenAPI specification from Apideck's official specification server (
specs.apideck.com). - References official documentation and API endpoints from Apideck (
developers.apideck.com,unify.apideck.com) and Kenjo (developers.kenjo.io).
Audit Metadata