The Agent Skills Directory

[SAFE]: The skill is a standard documentation and integration guide for the Kenjo HRIS connector via Apideck. All code examples and instructions are benign.
[CREDENTIALS_UNSAFE]: The skill follows security best practices by instructing users to store sensitive credentials like APIDECK_API_KEY and APIDECK_APP_ID in environment variables rather than hardcoding them.
[EXTERNAL_DOWNLOADS]: Referenced URLs and API endpoints point to official and well-known vendor domains, including apideck.com, kenjo.io, and github.com/apideck-libraries.
[PROMPT_INJECTION]: The skill interacts with external HRIS data, which represents a potential surface for indirect prompt injection.
Ingestion points: Data is ingested via the apideck.hris.employees.list method and Proxy API endpoints.
Boundary markers: The provided code snippets do not include explicit delimiters for untrusted API responses.
Capability inventory: The skill allows reading and syncing employees, departments, and payroll data.
Sanitization: No explicit data sanitization or validation logic is present in the documentation examples.
Note: This is a standard risk for data-integration skills and does not indicate malicious intent.

kenjo