The Agent Skills Directory

[PROMPT_INJECTION]: No malicious instruction overrides or bypass attempts were detected. The skill uses standard instructional language for its intended purpose.
[CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or secrets are present. Code examples correctly demonstrate using environment variables (e.g., process.env.APIDECK_API_KEY) and placeholders for sensitive identifiers.
[DATA_EXFILTRATION]: Network operations described are restricted to official vendor endpoints (unify.apideck.com). There are no attempts to access sensitive local files or send data to unauthorized external domains.
[EXTERNAL_DOWNLOADS]: The skill references the official @apideck/unify SDK and legitimate OpenAPI specifications from the vendor's trusted domain (specs.apideck.com).
[COMMAND_EXECUTION]: No dangerous shell commands, privilege escalation (sudo), or persistence mechanisms are present. The provided curl example is a standard API request to the vendor's proxy service.

acumatica