dingtalk-ai-web-search

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted content from web search results.
  • Ingestion points: Search result data is retrieved from a remote MCP server via the cmd_search function in scripts/search.sh.
  • Boundary markers: Results are formatted with clear labels such as '[1]', 'URL:', and '摘要:' (Snippet) to help the agent distinguish content.
  • Capability inventory: The skill performs network requests and configuration storage but does not execute the retrieved web content as code; it only presents text to the agent.
  • Sanitization: Snippets are truncated to a maximum of 300 characters, reducing the payload size of any potentially injected instructions.
  • [COMMAND_EXECUTION]: The skill uses a bash script to handle its core logic, including connectivity tests and search queries.
  • The scripts/search.sh script utilizes standard system tools like curl, grep, sed, and python to perform JSON-RPC requests to the search gateway.
  • Configuration is stored in a local .mcp_url file, allowing the tool to persist the search endpoint across sessions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 06:03 AM