The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data from sources such as inbound webhooks and user inputs, which represents a potential surface for indirect prompt injection. However, the skill explicitly mitigates this risk by providing specific security instructions to treat webhook payloads as untrusted and requiring sanitization of all fields before logging, rendering, or interpolation.
[COMMAND_EXECUTION]: The skill provides curl command templates for interacting with the Sinch Porting API. These commands are directed at legitimate vendor infrastructure (porting.api.sinch.com) and are used for standard administrative tasks like portability checks and order management.
[DATA_EXFILTRATION]: The skill manages sensitive data, including customer PII and carrier PINs. To prevent data exposure, it includes clear guidelines on storing credentials in environment variables rather than hardcoding them and provides instructions to avoid logging full sensitive payloads in production environments.

sinch-porting-api