How Effectively Do Security Skills Guide Coding Agents in Vulnerability Detection in Linux Kernel?

Summary

Researchers ran 37 security skills with Claude Code and four underlying LLMs on 100 real Linux kernel vulnerabilities across ten classes, totaling 14800 runs. Only 24.4 percent of runs located the correct function, and 15.7 percent correctly classified the vulnerability. The authors propose SKILL-SIF, a self-improving framework that evolves skills from missed vulnerabilities, raising fully correct detection on unseen vulnerabilities from 2 percent to 16 percent.

Topics

• AI agents

Related items

• InfoUS bans DeepSeek AI from government use as tech tension with China continuesSame vendor · BBC Technology
• InfoAnthropic commits 5% of shares to new public benefit fund that could address AI job disruptionSame vendor · CNBC Technology
• InfoThe Download: preserving the Arctic permafrost, and playful AI agentsSame vendor · MIT Technology Review
• InfoAI firm Anthropic to commit 5% of shares to fund for ‘public good’Same vendor · The Guardian Technology
• MediumFake Web3 Accelerator Uses npm Packages to Spread Malware and Hijack AI Agent TrafficSame vendor · The Hacker News