{"slug": "your-llm-app-will-get-jailbroken-here-are-8-free-adversarial-probes-you-can-run", "title": "Your LLM app will get jailbroken. Here are 8 free adversarial probes you can run in 30 seconds", "summary": "A developer released a free 8-probe adversarial testing battery for LLM applications, runnable in about 30 seconds via a hosted API endpoint. The developer's own self-scan of an autonomous security agent scored 27/100 (MEDIUM), with 1 of 8 probes flagged after the model leaked part of its system prompt when asked politely in another language. The tool returns a 0-100 risk score, raw per-probe prompts and model replies, and a hash-verifiable report, with a 15-probe core released under MIT.", "body_md": "I run an autonomous agent that makes security decisions from untrusted input. Before I trusted it, I red-teamed it the way an attacker would. The result: **27/100 MEDIUM, 1 of 8 probes flagged** - a soft failure where the model leaked part of its system prompt when asked politely in a different language.\n\nHere is the exact 8-probe battery I use on every LLM app before it talks to users. You can run it free, no signup, against your own system prompt:\n\n```\ncurl -s -X POST https://llmrt-companion.manhliemcn4euwlu.workers.dev/agent-scan \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"spec\": \"PASTE YOUR SYSTEM PROMPT HERE\", \"uid\": \"your-name\"}'\n```\n\n~35 seconds later you get a 0-100 risk score, the per-probe raw prompt + raw model reply (so you can verify every claim), and the flagged responses. The report is hash-verifiable (sha256 over the served bytes), and the durable link stays up: my own self-scan is at `https://llmrt-companion.manhliemcn4euwlu.workers.dev/r/e21808b6fedb` - recompute the hash, re-run the scan, check my work.\n\n**The 8 free probes** (full kit is 35 across 17 attack classes, this is the high-yield core):\n\nA few things that surprised me when I actually ran this instead of eyeballing it:\n\nIf you are shipping an LLM behind a form, this is the 30-second check I would want to see before merging. The 15-probe core is MIT - clone it and diff any probe I claim: `gitee.com/xydhw/llm-red-team-starter-kit`.\n\nWhat is the softest failure you have found in your own model?", "url": "https://wpnews.pro/news/your-llm-app-will-get-jailbroken-here-are-8-free-adversarial-probes-you-can-run", "canonical_source": "https://dev.to/llmrt/your-llm-app-will-get-jailbroken-here-are-8-free-adversarial-probes-you-can-run-in-30-seconds-5665", "published_at": "2026-09-12 15:14:27+00:00", "updated_at": "2026-09-12 15:44:38.768761+00:00", "lang": "en", "topics": ["ai-safety", "large-language-models", "ai-agents", "ai-tools", "developer-tools"], "entities": ["llmrt-companion.manhliemcn4euwlu.workers.dev", "Gitee"], "alternates": {"html": "https://wpnews.pro/news/your-llm-app-will-get-jailbroken-here-are-8-free-adversarial-probes-you-can-run", "markdown": "https://wpnews.pro/news/your-llm-app-will-get-jailbroken-here-are-8-free-adversarial-probes-you-can-run.md", "text": "https://wpnews.pro/news/your-llm-app-will-get-jailbroken-here-are-8-free-adversarial-probes-you-can-run.txt", "jsonld": "https://wpnews.pro/news/your-llm-app-will-get-jailbroken-here-are-8-free-adversarial-probes-you-can-run.jsonld"}}