extract-ssot

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

• Third-party content exposure detected (medium risk: 0.30). In the identify exhaustive mode and verify/emit-verify-facts.sh gates, the workflow reads git-tracked markdown from the consuming repository (including user-authored content) and feeds its free text into the LLM for clustering/evidence, so an outsider can inject poison by submitting/editing markdown that the required runtime scans.