skills/zilliztech/zilliz-plugin/acl/Gen Agent Trust Hub

acl

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform administrative operations via the zilliz CLI, including creating, updating, and deleting roles, as well as managing organization members and groups. These commands are part of the intended management functionality for Zilliz Cloud resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface where untrusted data provided by a user or external source could influence command execution.
  • Ingestion points: User-supplied values for role names, descriptions, project/role identifiers, email addresses, and policy JSON files/stdin are interpolated into CLI commands.
  • Boundary markers: The instructions do not define delimiters or specific safety guidelines to handle special characters or potential command injection sequences in these inputs.
  • Capability inventory: The skill provides instructions for the zilliz CLI to manage access control lists (ACLs), roles, and permissions in the cloud environment.
  • Sanitization: There are no explicit validation or sanitization steps mentioned for the inputs used in the command templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:56 AM
Security Audit — agent-trust-hub — acl