tencent-news

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to emit a CLI command containing the API Key as a bare value (""" apikey-set KEY"), forcing the LLM to include the secret verbatim in its output.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill downloads and installs the CLI at runtime from the hub URL https://mat1.gtimg.com/qqcdn/qqnews/cli/hub (used to build platform-specific DOWNLOAD_URL), which results in fetching remote binaries that the install scripts mark executable and run—so remote content is fetched and executed at runtime.