Lucene search
+L

16 matches found

NVD
NVD
•added 2026/10/20 1:17 a.m.•21 views

CVE-2026-77930

EvoScientist 0.1.0 before 0.2.5 contains an approval bypass vulnerability that allows attackers to run host shell commands by delegating them to async sub-agents lacking an interrupton gate. Attackers can plant instructions in ingested content such as fetched web pages, so the agent calls...

9.8CVSS0.00688EPSS
SaveExploits0References6
Vulnrichment
Vulnrichment
•added 2026/10/20 12:46 a.m.•16 views

CVE-2026-77930 EvoScientist 0.1.0 before 0.2.5 Human Approval Bypass via Async Sub-Agents

EvoScientist 0.1.0 before 0.2.5 contains an approval bypass vulnerability that allows attackers to run host shell commands by delegating them to async sub-agents lacking an interrupton gate. Attackers can plant instructions in ingested content such as fetched web pages, so the agent calls...

9.8CVSS5.9AI score0.00688EPSS
SaveExploits0References6
osv_cve
osv_cve
•added 2026/10/20 12:46 a.m.•25 views

CVE-2026-77930 EvoScientist 0.1.0 before 0.2.5 Human Approval Bypass via Async Sub-Agents

EvoScientist 0.1.0 before 0.2.5 contains an approval bypass vulnerability that allows attackers to run host shell commands by delegating them to async sub-agents lacking an interrupton gate. Attackers can plant instructions in ingested content such as fetched web pages, so the agent calls...

9.3CVSS5.9AI score0.00688EPSS
SaveExploits0References10
Mend
Mend
•added 2026/10/20 12:46 a.m.•19 views

CVE-2026-77930

EvoScientist 0.1.0 before 0.2.5 contains an approval bypass vulnerability that allows attackers to run host shell commands by delegating them to async sub-agents lacking an interrupton gate. Attackers can plant instructions in ingested content such as fetched web pages, so the agent calls...

8.8CVSS5.9AI score0.00688EPSS
SaveExploits0References6
Cvelist
Cvelist
•added 2026/10/20 12:46 a.m.•32 views

CVE-2026-77930 EvoScientist 0.1.0 before 0.2.5 Human Approval Bypass via Async Sub-Agents

EvoScientist 0.1.0 before 0.2.5 contains an approval bypass vulnerability that allows attackers to run host shell commands by delegating them to async sub-agents lacking an interrupton gate. Attackers can plant instructions in ingested content such as fetched web pages, so the agent calls...

9.8CVSS0.00688EPSS
SaveExploits0References6
EUVD
EUVD
•added 2026/10/20 12:46 a.m.•17 views

EUVD-2026-104687

EvoScientist 0.1.0 before 0.2.5 contains an approval bypass vulnerability that allows attackers to run host shell commands by delegating them to async sub-agents lacking an interrupton gate. Attackers can plant instructions in ingested content such as fetched web pages, so the agent calls...

8.8CVSS5.9AI score0.00688EPSS
SaveExploits0References6
CVE
CVE
•added 2026/10/20 12:46 a.m.•41 views

CVE-2026-77930

EvoScientist versions 0.1.0 before 0.2.5 are vulnerable to an approval bypass vulnerability. The root cause is the use of async sub-agents that lack an interrupt_on gate, which allows attackers to execute arbitrary host shell commands. By planting malicious instructions in ingested content, such ...

9.8CVSS5.9AI score0.00688EPSS
SaveExploits0References6
Positive Technologies
Positive Technologies
•added 2026/10/20 12:00 a.m.•23 views

PT-2026-117949

EvoScientist 0.1.0 before 0.2.5 contains an approval bypass vulnerability that allows attackers to run host shell commands by delegating them to async sub-agents lacking an interrupt on gate. Attackers can plant instructions in ingested content such as fetched web pages, so the agent calls start...

8.8CVSS5.9AI score0.00688EPSS
SaveExploits0References7
Positive Technologies
Positive Technologies
•added 2026/10/10 12:00 a.m.•19 views

PT-2026-109735

Phi 0.3.0 through 0.28.4 contains a permission bypass vulnerability that allows spawned sub-agents to escape workspace only writes and readonly mode by supplying an unchecked workdir to agent spawn. Attackers can plant prompt-injected instructions in processed content so the agent spawns a worker...

6CVSS6AI score0.00315EPSS
SaveExploits0References6
NVD
NVD
•added 2026/05/28 6:16 p.m.•45 views

CVE-2026-45374

CodeWhale is a DeepSeek + MiMo coding agent in terminal. Prior to 0.8.26, the taskcreate tool spawns durable sub-agents that inherit two insecure defaults, allowshell defaults to true config.rs:1499: self.allowshell.unwraportrue and autoapprove defaults to true taskmanager.rs:297: autoapprove:...

9.6CVSS0.00387EPSS
SaveExploits0References2
osv_cve
osv_cve
•added 2026/05/28 5:26 p.m.•32 views

CVE-2026-45374 CodeWhale: task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files

CodeWhale is a DeepSeek + MiMo coding agent in terminal. Prior to 0.8.26, the taskcreate tool spawns durable sub-agents that inherit two insecure defaults, allowshell defaults to true config.rs:1499: self.allowshell.unwraportrue and autoapprove defaults to true taskmanager.rs:297: autoapprove:...

9.6CVSS6AI score0.00387EPSS
SaveExploits0References4
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/05/28 12:00 a.m.•15 views

CVE-2026-45374: Improper Control of Generation of Code

CodeWhale is a DeepSeek + MiMo coding agent in terminal. Prior to 0.8.26, the taskcreate tool spawns durable sub-agents that inherit two insecure defaults, allowshell defaults to true config.rs:1499: self.allowshell.unwraportrue and autoapprove defaults to true taskmanager.rs:297: autoapprove:...

9.6CVSS6AI score0.00387EPSS
SaveExploits0References2
Github Security Blog
Github Security Blog
•added 2026/05/14 8:29 p.m.•63 views

DeepSeek TUI: task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files

Summary The taskcreate tool spawns durable sub-agents that inherit two insecure defaults: - allowshell defaults to true config.rs:1499: self.allowshell.unwraportrue - autoapprove defaults to true taskmanager.rs:297: autoapprove: Sometrue When a user approves a taskcreate call which requires...

9.6CVSS5.9AI score0.00387EPSS
SaveExploits0References5Affected Software1
osv_ghsa
osv_ghsa
•added 2026/05/14 8:29 p.m.•58 views

GHSA-72W5-PF8H-XFP4 DeepSeek TUI: task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files

Summary The taskcreate tool spawns durable sub-agents that inherit two insecure defaults: - allowshell defaults to true config.rs:1499: self.allowshell.unwraportrue - autoapprove defaults to true taskmanager.rs:297: autoapprove: Sometrue When a user approves a taskcreate call which requires...

9.6CVSS5.9AI score0.00387EPSS
SaveExploits0References5
Positive Technologies
Positive Technologies
•added 2026/05/14 12:00 a.m.•66 views

PT-2026-41186

Name of the Vulnerable Software and Affected Versions CodeWhale versions prior to 0.8.26 Description The task create tool spawns durable sub-agents that inherit insecure default settings. Specifically, the allow shell variable defaults to true and the auto approve variable defaults to true. When ...

9.6CVSS6.3AI score0.00387EPSS
SaveExploits0References10
GithubExploit
GithubExploit
•added 2026/04/09 3:04 p.m.•137 views

cybersentinel-agent

CyberSentinel Agent Defensive cybersecurity agent framework w...

6.1AI score
SaveExploits0
Rows per page
Query Builder