grilling

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

• Third-party content exposure detected (high risk: 0.70). The required workflow instructs the agent to read prior content from an outsider-authored/free-form Obsidian vault file (e.g., ~/Obsidian/CLAUDE.md) at runtime for the “topic sweep,” which would allow embedded text (and potential prompt injection) to be fed into the LLM context.