om-auto-implement-issue

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text from the tracker issue is fetched at runtime via the get-issue operation (issue title/body/comments), and that untrusted prose is then used to generate the spec/PR content, which feeds it into the agent’s LLM context (indirect prompt-injection risk).