cubrid-common

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 cubrid_fetch_pr_json, which calls gh api to fetch GitHub PR JSON (including the PR body field) and then returns it to the caller; that PR body is outsider-authored content and is readable text that may be embedded into the agent’s LLM context.