keka
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines an integration for reading HRIS data, which inherently introduces a potential surface for indirect prompt injection.\n
- Ingestion points: The skill facilitates fetching employee, department, and payroll records from Keka HR via the Apideck HRIS unified API as seen in
SKILL.md.\n - Boundary markers: There are no explicit instructions or delimiters defined to isolate the fetched external data from the agent's instructions.\n
- Capability inventory: The skill enables network operations via the Apideck API and the Proxy API, which could be leveraged to interact with other Keka HR endpoints (
SKILL.md).\n - Sanitization: No specific sanitization or filtering logic for external data is provided in the skill instructions.\n- [SAFE]: All external references and domains point to official vendor infrastructure associated with Apideck and Keka HR (
apideck.com,unify.apideck.com,keka.com).\n- [SAFE]: The skill correctly promotes the use of environment variables for API keys and identifiers, adhering to best practices for credential management.
Audit Metadata