producthunt-launch-images

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

• Third-party content exposure detected (high risk: 0.75). The required workflow includes “Inspect Product Hunt examples or search current launch images first” and “use web search, browser snapshots, cached snippets, screenshots…”, which at runtime can ingest outsider-authored free text from public web pages into the agent’s LLM context via fetched/search/browsed content.