dingtalk-channel-connect

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to read and "展示" (display) the DingTalk Client ID and the real Client Secret from the credentials page, which requires the LLM to handle and output secret values verbatim, creating an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly opens and snapshots the public DingTalk developer site (https://open-dev.dingtalk.com/) and instructs the agent to re-read page text/structure to locate elements and to download user-provided image links, so it ingests and acts on untrusted third-party web content described in the SKILL.md workflow.