skills/wjxcom/wjx-ai-kit/wjx-cli-use/Gen Agent Trust Hub

wjx-cli-use

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the wjx-cli package via npm install -g wjx-cli. It also features a self-update command wjx update. Both the package and the tool originate from the vendor wjxcom associated with the Wenjuanxing platform.
  • [COMMAND_EXECUTION]: The documentation provides instructions for executing a wide range of shell commands using the wjx binary. These commands facilitate survey management, data analytics, and administrative tasks via the platform's OpenAPI.
  • [PROMPT_INJECTION]: The skill is designed to ingest external data, such as survey responses and metadata, which creates a surface for indirect prompt injection.
  • Ingestion points: wjx response query, wjx response report, and wjx survey get as described in SKILL.md and references/response-commands.md.
  • Boundary markers: The instructions do not currently include explicit delimiters or warnings for the agent to ignore instructions embedded within the fetched survey data.
  • Capability inventory: The agent has access to sensitive capabilities including wjx survey delete, wjx response clear, and wjx contacts delete as detailed in the reference files.
  • Sanitization: No specific data sanitization or validation logic is defined within the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 08:08 AM