{"slug": "fable-5-update-still-willing-to-cybercrime", "title": "Fable 5 Update: Still Willing To Cybercrime", "summary": "Anthropic's Fable 5 model, when used in the Claude Code or Cursor agent harness, can be easily prompted to help users commit cybercrime by exploiting real vulnerabilities in IoT devices, removing the skill floor for carrying out attacks at unprecedented scale and speed.", "body_md": "Weeks ago, I found that Anthropic’s Fable 5 was more than willing to help users commit cybercrime—planning and actively exploiting (albeit somewhat known) vulnerabilities against IoT devices all over the internet. Extremely basic prompt engineering was all it took to bypass the guardrails.\n\nThese aren’t sophisticated 0days but they’re still real vulnerabilities. Anyone motivated enough can find and exploit them. The issue is that Fable 5 *in the Claude Code or Cursor agent harness* removes the skill floor and helps a complete imbecile carry out these attacks…at a scale and speed we’ve never seen before, even from a state-sponsored actor, well, except maybe Fancy Bear. against anyone, anywhere. Human effort and time used to be a meaningful deterrent. That’s gone now. Yay /s", "url": "https://wpnews.pro/news/fable-5-update-still-willing-to-cybercrime", "canonical_source": "https://alec.is/posts/fable-5-update-still-willing-to-cybercrime/", "published_at": "2026-07-01 17:07:14+00:00", "updated_at": "2026-07-13 15:40:54.190881+00:00", "lang": "en", "topics": ["ai-safety", "ai-ethics", "large-language-models", "ai-agents"], "entities": ["Anthropic", "Fable 5", "Claude Code", "Cursor"], "alternates": {"html": "https://wpnews.pro/news/fable-5-update-still-willing-to-cybercrime", "markdown": "https://wpnews.pro/news/fable-5-update-still-willing-to-cybercrime.md", "text": "https://wpnews.pro/news/fable-5-update-still-willing-to-cybercrime.txt", "jsonld": "https://wpnews.pro/news/fable-5-update-still-willing-to-cybercrime.jsonld"}}