datadog-cli

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly connects to external Datadog instances (e.g., app.datadoghq.com) and its required workflows and commands in SKILL.md, README.md, and references (logs search/tail/trace, dashboards get/update, etc.) fetch and interpret customer-generated logs and dashboards—which the agent reads and can use to drive follow-up actions (including destructive updates)—so untrusted third-party content can influence behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs running the remote CLI via npx (npx @leoflores/datadog-cli) and references the repository https://github.com/leonardocouy/datadog-cli, which means code is fetched and executed at runtime and is a required dependency for the skill.