data-scraper-agent

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

• Third-party content exposure detected (high risk: 0.95). Outsider free text is ingested into the LLM via the runtime scraping path (scraper/sources/* fetches public/third-party HTML/RSS/JSON, then scraper/main.py passes the resulting item text into ai/pipeline.py → _build_prompt() → ai/client.py → generate(prompt)), so the LLM context can include arbitrary outsider-authored content from those sources.