gitlab

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 when the agent uses Apideck’s Issue Tracking connector to fetch GitLab issues/comments (user-authored content from the GitLab tenant) and then passes that retrieved prose into the agent for summarization/response; this is not authored by the operating user.