doubt-driven-development

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md describes sending first-party “ARTIFACT + CONTRACT” text into a fresh-context reviewer (Claude Code agents/ orchestration) and optionally piping a constructed prompt file into external CLIs, but it does not indicate any runtime ingestion of outsider-authored free text from public feeds/queues/issues/tickets without the user/agent first selecting/using specific artifact inputs.