Developer open-sources LLM-driven pentest platform ARTEX
11/22/2026 — 11/22, 13:18·1 sources (all)·1 reports (all)
Key takeaways
- A developer detailed ARTEX, a self-hosted LLM-driven penetration testing platform that ties each finding to the exact request and response s…
Background & analysis
On 2026-11-22 at 12:55, a developer posted on cnblogs to introduce ARTEX, a self-hosted, LLM-driven penetration testing platform. The developer described first asking AI to run a security review on an older project, only to find the report open with a conclusion labeled "high risk: unauthorized access" but no evidence attached, such as the specific request or response involved. After manually reproducing each item one by one, the developer found that most of them turned out to be false positives, which highlighted two persistent gaps in AI-based vulnerability scanning: findings carry no source, and scans rarely state clearly what was tested and what was not.
ARTEX is built to close both gaps. Its central approach is to tie every vulnerability finding to the concrete request and response behind it, so users can replay that request and verify the finding on their own. The platform does not leave the model to improvise freely. Instead, a planner first breaks the target down into a set of intents, and workers then execute those intents with real tools, writing the results into two cross-referenced graphs. One is a target inventory that records what exists on the target, and the other is a test log that records what was tried, what came back, and why. The two graphs are linked by anchors, allowing users to trace how each item on the inventory was tested rather than reading a pile of scattered conclusions. ARTEX also adds an approval gate, scope and denylist controls, and token and round budgets. As of now, the platform has only been made public through this developer write-up, and no further progress has been reported.
AI-generated from 1 reports · updated 24 minutes ago
- Heat index
- 98
- All sources
- 1
- All reports
- 1
- First seen
- 54 minutes ago
Reports on this story headlines open the original
A developer writes up ARTEX, a self-hosted, LLM-driven penetration testing platform that binds every finding to a specific request and response so results can be replayed and checked. Per the post, a planner splits targets into intents, workers run real tools, and two cross-linked graphs record what exists and what was tested, with approval gates, scope denylists and token/round budgets.
博客园AI score 52
Other stories people are talking about
- Heat index 1205RisingLean Community verifies Anthropic and Claude Riemann hypothesis proof22 sources
- Heat index 1048Anthropic Reaches $1.6 Trillion Market Value in First Trading Week After IPO21 sources
- Heat index 546RisingThinking Machines Lab Open-Sources Inkling 2 Mini with 32GB Model Card Recommendation10 sources
- Heat index 523Anthropic IPO total raise reaches $93.5 billion after greenshoe exercise18 sources
- Heat index 449SEC probes Nvidia accounting practices as shares post seven-week slide9 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

