The Agent Skills Directory

[DATA_EXPOSURE]: The skill provides detailed guidance for managing sensitive authentication materials such as webhook secrets and OAuth tokens. It correctly advises developers to keep webhook secrets server-side and use environment variables for configuration. The documentation also highlights that the SDK automatically redacts sensitive parameters (e.g., tokens, passwords, and secrets) from error logs to prevent accidental exposure.
[INDIRECT_PROMPT_INJECTION]: The skill documentation addresses the ingestion of untrusted data from external Bitrix24 events and webhooks.
Ingestion points: External data enters the system through outbound webhooks and OAuth install/refresh events as described in SKILL.md.
Boundary markers: The documentation explicitly recommends verifying the application_token against a trusted value to ensure the integrity of the event source.
Capability inventory: The skill facilitates REST API interactions and token persistence.
Sanitization: The documentation includes clear instructions for HTML-escaping user-provided content before it is transmitted to messaging or chat interfaces.

b24jssdk-core