skills/modelstudioai/cli/bailian-kb/Gen Agent Trust Hub

bailian-kb

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the 'kb_manage' tool to execute various commands for the 'bailian-cli' ('bl'), covering the full lifecycle of knowledge bases, retrieval services, and data center files.- [EXTERNAL_DOWNLOADS]: The instructions suggest the installation of 'bailian-cli' if it is missing from the host environment. This is the official management tool for Alibaba Cloud's Bailian platform.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external documents from local storage or Alibaba Cloud OSS. Malicious content within these files could attempt to manipulate the agent's behavior during document management or debugging steps. * Ingestion points: 'bl knowledge doc upload' (local files) and 'bl knowledge doc import-oss' (OSS buckets). * Boundary markers: No specific delimiters or safety instructions are provided to the agent for handling the content of these documents. * Capability inventory: Command execution via 'kb_manage' for managing knowledge bases and retrieval services. * Sanitization: There are no explicit instructions for validating or sanitizing the content of the ingested files.- [DYNAMIC_EXECUTION]: The skill dynamically constructs command arguments for the 'kb_manage' tool based on user requests, which is necessary for its functionality as a CLI management interface.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 08:27 PM