Unverified50% confidenceSolutionExact time
In penetration testing scenarios, models with tool-calling capabilities can chain together specialized tools such as Nmap port scanning, the Metasploit exploitation framework, and SQL injection probing.
1
Sources
50%
Confidence
Long-term
Relevance
9/19/2026
First Seen
Sources
Related Entities
Related Claims
Unverified安全研究已证明大语言模型能够自主执行渗透测试流程，包括信息收集、漏洞扫描、漏洞利用和权限提升75% similarUnverifiedIn a live demonstration, the large model successfully discovered an SQL injection vulnerability through MCP automated testing, automatically sending injection payloads to the edit1 interface and determining the injection point based on the returned error information.72% similarUnverifiedEncapsulating complete penetration testing processes (such as XSS detection and SQL injection detection) into reusable Skills can improve testing efficiency.72% similarUnverifiedCompanies internally arrange penetration testing tasks and calculate security personnel performance based on the number of vulnerabilities discovered.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/934704API
curl https://kongchang.com/api/v1/knowledge/claims/934704MCP
get_claim(id=934704)