datadog-automation

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via DATADOG_SEARCH_LOGS (and other Datadog “GET/LIST” tools) because the runtime ingests returned log/event/monitor/dashboard text authored by external systems/users, which the agent then uses in its reasoning.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill requires connecting to the external MCP endpoint https://rube.app/mcp and calling RUBE_SEARCH_TOOLS at runtime to fetch tool schemas, so remote content from that URL can directly control the agent's tools/instructions.