The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected. The skill instructions and code samples are consistent with legitimate integration practices for the Personio HRIS service.
[DATA_EXFILTRATION]: The skill correctly handles sensitive credentials by referencing environment variables (APIDECK_API_KEY, APIDECK_APP_ID) instead of hardcoding secrets.
[EXTERNAL_DOWNLOADS]: All external references target official vendor domains (apideck.com, personio.de) or official package registries. The dependency on @apideck/unify is a legitimate vendor-owned library.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from Personio (e.g., employee records, time-off requests) into the agent context.
Ingestion points: External data is fetched via the apideck.hris.employees.list method described in SKILL.md.
Boundary markers: None explicitly defined in the provided instructions.
Capability inventory: The skill facilitates read-access to HRIS data; it does not explicitly define write or system-level capabilities in its own logic.
Sanitization: No specific sanitization or filtering logic is provided for the external data before it is processed by the agent.

personio