execution-gitlab-issue

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

• Third-party content exposure detected (high risk: 0.95). Yes: the workflow’s Phase 2 step 1 explicitly reads the full GitLab issue payload (title/description/comments/attachments) from an outsider-authored issue URL via MCP, and then passes that issue payload into the code-autonomous LLM context (Engine mode), creating indirect prompt-injection exposure through issue free text.