Lucene search
+L

25 matches found

CNNVD
CNNVD
•added 2026/04/09 12:00 a.m.•21 views

TaskFlow AI 操作系统命令注入漏洞

TaskFlow AI is an AI thinking flow orchestration and visualization engine developed by Agions’ individual developers. Versions of TaskFlow AI such as 2.1.8 and earlier contained a vulnerability related to operating system command injection. This vulnerability stemmed from an unknown function in t...

6.5CVSS6.6AI score0.01817EPSS
SaveExploits0References7
Positive Technologies
Positive Technologies
•added 2026/04/09 12:00 a.m.•29 views

PT-2026-31565

Name of the Vulnerable Software and Affected Versions Agions taskflow-ai versions through 2.1.8 Description A security flaw exists in Agions taskflow-ai up to version 2.1.8. The issue impacts an unknown function within the src/mcp/server/handlers.ts file of the terminal execute component, leading...

6.5CVSS6.5AI score0.01817EPSS
SaveExploits0References12
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/04/09 12:00 a.m.•1 views

CVE-2026-5831: Improper Neutralization of Special Elements used in an OS Command

A security flaw has been discovered in Agions taskflow-ai up to 2.1.8. This impacts an unknown function of the file src/mcp/server/handlers.ts of the component terminalexecute. Performing a manipulation results in os command injection. The attack is possible to be carried out remotely. Upgrading ...

6.5CVSS5.2AI score0.01817EPSS
SaveExploits0References3
Github Security Blog
Github Security Blog
•added 2026/03/06 9:09 p.m.•41 views

How to scan for vulnerabilities with GitHub Security Lab’s open source AI-powered framework

For the last few months, we've been using the GitHub Security Lab Taskflow Agent along with a new set of auditing taskflows that specialize in finding web security vulnerabilities. They also turn out to be very successful at finding high-impact vulnerabilities in open source projects. As security...

6.6AI score
SaveExploits0
Github Security Blog
Github Security Blog
•added 2026/01/14 6:45 p.m.•15 views

Community-powered security with AI: an open source framework for security research

Since its founding in 2019, GitHub Security Lab has had one primary goal: community-powered security. We believe that the best way to improve software security is by sharing knowledge and tools, and by using open source software so that everybody is empowered to audit the code and report any...

5.8AI score
SaveExploits0
Rows per page
Query Builder