keka
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides standard integration instructions for the Keka HR service via Apideck. No malicious patterns, obfuscation, or unauthorized access attempts were detected.
- [EXTERNAL_DOWNLOADS]: Documentation and configuration resources are fetched from well-known and trusted domains, including apideck.com and keka.com. These references are used for official API specifications and documentation.
- [CREDENTIALS_UNSAFE]: The skill demonstrates secure practices by using environment variables (e.g., APIDECK_API_KEY) for secret management in its code examples, preventing the exposure of sensitive tokens.
- [PROMPT_INJECTION]: The skill retrieves data from external HRIS records, which presents an inherent surface for indirect prompt injection. 1. Ingestion points: Data retrieved via the apideck.hris.employees.list method described in SKILL.md. 2. Boundary markers: None explicitly defined to separate retrieved data from the agent's prompt context. 3. Capability inventory: The skill facilitates API requests through the Apideck SDK and a Proxy API. 4. Sanitization: No explicit validation or filtering of incoming data is described in the integration logic.
Audit Metadata