sourcebot

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

• Third-party content exposure detected (high risk: 0.95). The required workflow uses Sourcebot MCP search_code (scoped by filterByRepoIds) and get_file_source to fetch and ingest readable code/text from outsider-authored public repositories at runtime (e.g., GitHub owner/repo contents), which can include indirect prompt-injection payloads.