baoyu-format-markdown

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

• Third-party content exposure detected (high risk: 0.75). The required workflow reads the user-specified file content (which can be outsider-authored) and then uses it as input to the LLM-driven analysis/formatting steps (Step 2/3/4), so arbitrary outsider text can enter the agent’s LLM context via the file’s body text.