dingtalk-ding

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill facilitates DingTalk DING message management through the dws CLI. The operations described (sending, recalling, and listing messages) are legitimate uses of the DingTalk API and CLI.- [COMMAND_EXECUTION]: The skill uses the dws binary to perform DING operations. This is the intended purpose of the skill and follows standard CLI interaction patterns.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it retrieves external message content using dws ding message list. This is a standard risk for messaging applications and is noted as a design characteristic rather than a vulnerability in this context.
  • Ingestion points: Message text from dws ding message list in references/ding.md.
  • Boundary markers: None.
  • Capability inventory: CLI commands for DING message management.
  • Sanitization: Relies on platform-level security.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 11:21 AM
Security Audit — agent-trust-hub — dingtalk-ding