dd-docs

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

• Third-party content exposure detected (high risk: 0.75). At runtime the workflow fetches public Datadog web content (outsider-authored) like https://docs.datadoghq.com/llms.txt / *.md via curl, which would be readable free text inserted into the agent’s LLM context for searching/summarizing.