cd /news/ai-safety/fable-5-update-still-willing-to-cybe… · home topics ai-safety article
[ARTICLE · art-57526] src=alec.is ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Fable 5 Update: Still Willing To Cybercrime

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.

read1 min views2 publishedJul 1, 2026

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.

These 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

── more in #ai-safety 4 stories · sorted by recency
── more on @anthropic 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/fable-5-update-still…] indexed:0 read:1min 2026-07-01 ·