The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of data from external Bitrix24 REST API endpoints, which presents an attack surface for indirect prompt injection.\n
Ingestion points: Data enters the agent's context through REST API responses from methods like actions.v2.call.make and actions.v3.callList.make in SKILL.md.\n
Boundary markers: The SDK uses structured AjaxResult objects, but the skill does not implement specific boundary delimiters to prevent the agent from potentially following instructions embedded within data fields.\n
Capability inventory: The skill provides methods for executing network requests to Bitrix24 servers and managing the resulting data sets as documented in SKILL.md.\n
Sanitization: The documentation describes a redactSensitiveParams feature for logs, but does not specify a process for sanitizing or escaping the data returned from API calls before agent interaction.\n- [EXTERNAL_DOWNLOADS]: The skill utilizes the @bitrix24/b24jssdk package and references documentation on bitrix24.github.io, which are official resources provided by the vendor.

b24jssdk-rest