ssotchk

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

• Third-party content exposure detected (high risk: 0.70). The workflow explicitly requires enumerating occurrences across “files, docs, wikis, tickets, channels, code, config” (including wikis/tickets/channels that are commonly outsider-authored), and then classifying and reporting their text back into the agent’s LLM context, which can include free-form outsider content at runtime.