Skills
skills/dingtalk-real-ai/dingtalk-workspace-cli/dingtalk-devdoc/Gen Agent Trust Hub

dingtalk-devdoc

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the dws command-line utility to perform documentation searches on the DingTalk Open Platform.
  • Evidence: SKILL.md and references/devdoc.md specify the use of dws devdoc article search to retrieve information based on user queries.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a standard attack surface where untrusted user input is passed to a CLI tool, and external documentation content is returned to the agent.
  • Ingestion points: User queries are passed to the --query flag in the dws command, as seen in references/devdoc.md.
  • Boundary markers: The command examples use double quotes to wrap the query strings.
  • Capability inventory: The skill uses the dws binary to search for articles, error codes, and API details.
  • Sanitization: No explicit sanitization or output filtering is defined within the skill files; the agent is instructed to use the returned links for further browsing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 11:20 AM
Security Audit — agent-trust-hub — dingtalk-devdoc