The Agent Skills Directory

[SAFE]: The skill facilitates integration with Remote through the vendor's unified API. Communications are restricted to official vendor domains, including unify.apideck.com, apideck.com, and specs.apideck.com.
[SAFE]: Sensitive credentials are managed using environment variables (e.g., APIDECK_API_KEY, APIDECK_APP_ID) and the vendor's Vault service, which is a recommended practice for secure API integration.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources (Remote's HRIS records) which could potentially contain malicious content designed to influence agent behavior.
Ingestion points: Data enters the agent context via HRIS API methods (e.g., apideck.hris.employees.list) and the Proxy API as described in SKILL.md.
Boundary markers: The instructions do not explicitly mandate the use of delimiters or "ignore" instructions when processing the ingested external data.
Capability inventory: The skill provides capabilities for network operations (via curl examples) and code execution within a Node.js environment.
Sanitization: No specific sanitization, validation, or filtering of the external data content is defined in the provided files.

remote