The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill integrates with external HRIS data (employees, payroll) via the Apideck API, which introduces a potential attack surface for indirect prompt injection if data retrieved from Simployer One contains malicious instructions.
Ingestion points: Data is ingested via apideck.hris.employees.list() and other HRIS endpoints mentioned in SKILL.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are provided in the examples.
Capability inventory: The skill allows listing, syncing, and proxying requests to the Simployer One API.
Sanitization: No explicit sanitization or validation of the retrieved HRIS data is shown in the provided examples.
[EXTERNAL_DOWNLOADS]: The skill references official vendor resources, including Apideck's unified API documentation and Simployer One's homepage. These are well-known services related to the skill's primary purpose.
[CREDENTIALS_UNSAFE]: The code examples correctly demonstrate using environment variables (process.env.APIDECK_API_KEY) for authentication, which is a secure practice for managing API credentials.

alexishr