img-gen-prompts

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

• Third-party content exposure detected (high risk: 0.70). The required workflow’s runtime path reads the archive search results (including outsider-authored source_prompt/author/source_url) via scripts/oip.py → run_library(...) → scripts/prompt_library.py into JSON that is then rendered/used by the gallery session, so outsider free text can enter the agent/LLM context indirectly through these fields.