The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill interfaces with external Zscaler APIs, creating a potential attack surface for indirect prompt injection.
Ingestion points: Tools like get_application_segment, list_access_policies, and get_app_connector retrieve data from external environments into the agent's context (SKILL.md).
Boundary markers: The skill documentation lacks explicit delimiters or instructions to ignore commands that might be embedded in the retrieved API data.
Capability inventory: The skill includes administrative write tools such as create_application_segment, update_application_segment, and delete_application_segment (SKILL.md).
Sanitization: No data validation or sanitization mechanisms for API responses are defined in the skill instructions.

zscaler-zpa