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

dingtalk-contact

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the dws binary through the scripts/contact_dept_members.py script. The implementation uses list-based arguments for subprocess.run, which is a secure method to prevent shell command injection from user-provided queries.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from DingTalk directory services.\n
  • Ingestion points: Data returned from dws calls in scripts/contact_dept_members.py and user queries entered in SKILL.md.\n
  • Boundary markers: Absent; there are no specific markers to distinguish data from instructions in the command outputs.\n
  • Capability inventory: Subprocess execution for reading and updating DingTalk directory records via dws.\n
  • Sanitization: The script uses secure sub-process handling to prevent system-level command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 05:05 PM
Security Audit — agent-trust-hub — dingtalk-contact