create-partner

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

• Third-party content exposure detected (high risk: 0.90). The skill's required intake workflow (Step 2 — "Import Raw Materials" in SKILL.md) and associated tools (e.g., tools/chat_parser.py, email_parser.py, Claude Vision for screenshots, and "paste social media posts/notes") explicitly ingest user-provided/untrusted chat logs, emails and social-media text and then use that content in the State Engine / Policy Selector / Counterfactual Engine to drive decisions and generate verbatim scripts, creating a clear path for indirect prompt injection.