blog-humanize-fast

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is the user-provided blog body loaded at runtime via agent(readInputPrompt, ...) from A.inputPath, and then that text is embedded into multiple LLM sub-prompts (e.g., rewritePrompt(c.text) and fidelityPrompt(orig, rewritten)), creating an indirect prompt-injection surface.