agent-dd

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes a command that asks the user to supply API and application keys directly as command-line arguments (agent-dd org add ... --api-key --app-key ), which requires embedding secret values verbatim in generated commands/outputs and poses a high exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.75). The required workflow involves fetching and ingesting Datadog monitor/log/trace/incident content at runtime (e.g., via logs search, monitors get, incidents get), which is outsider-authored free text from Datadog systems into the agent’s LLM context.