Lucene search
K

123 matches found

Vulnrichment
Vulnrichment
added 2026/05/18 6:57 p.m.9 views

CVE-2026-45244 Summarize < 0.15.1 Unapproved Browser Automation Execution

Summarize prior to 0.15.1 contains a missing authorization vulnerability that allows attackers to execute browser automation actions without per-call user approval when the extension automation feature is enabled. Attackers can influence the agent through malicious page or summary content to invo...

5.4CVSS5.9AI score0.00027EPSS
Exploits1References4
Cvelist
Cvelist
added 2026/05/18 6:57 p.m.20 views

CVE-2026-45244 Summarize < 0.15.1 Unapproved Browser Automation Execution

Summarize prior to 0.15.1 contains a missing authorization vulnerability that allows attackers to execute browser automation actions without per-call user approval when the extension automation feature is enabled. Attackers can influence the agent through malicious page or summary content to invo...

5.4CVSS0.00027EPSS
Exploits1References4
CNNVD
CNNVD
added 2026/05/18 12:0 a.m.4 views

Summarize 安全漏洞

Summarize is a multi-source rapid summarization tool developed by Peter Steinberger. Versions of Summarize prior to 0.15.1 contain security vulnerabilities. These vulnerabilities stem from an issue with authorization deficiencies, which could allow attackers to execute browser automation operatio...

5.4CVSS5.9AI score0.00027EPSS
Exploits1References1
Cvelist
Cvelist
added 2026/04/28 6:10 p.m.22 views

CVE-2026-42423 OpenClaw < 2026.4.8 - strictInlineEval Approval Boundary Bypass via Approval-Timeout Fallback

OpenClaw before 2026.4.8 contains an approval-timeout fallback mechanism that bypasses strictInlineEval explicit-approval requirements on gateway and node exec hosts. Attackers can exploit this timeout fallback to execute inline eval commands that should require explicit user approval,...

7.7CVSS0.00054EPSS
Exploits0References3
EUVD
EUVD
added 2026/04/28 6:9 p.m.0 views

EUVD-2026-26098

OpenClaw before 2026.3.28 contains an exec allowlist bypass vulnerability where allow-always persistence fails to unwrap /usr/bin/script and similar wrappers before storing trust decisions. Attackers can obtain user approval for one wrapped command to persist trust for wrapper binaries that execu...

7.3CVSS5.3AI score0.00026EPSS
Exploits0References2
CVE
CVE
added 2026/04/28 6:9 p.m.3 views

CVE-2026-41390

CVE-2026-41390 affects OpenClaw prior to 2026.3.28. The vulnerability is an exec allowlist bypass where allow-always persistence does not unwrap wrappers (e.g., /usr/bin/script) before storing trust decisions, enabling a user-approved wrapped command to persist trust for a wrapper that later exec...

7.3CVSS5.3AI score0.00026EPSS
Exploits0References2Affected Software1
ATTACKERKB
ATTACKERKB
added 2026/04/28 6:9 p.m.0 views

CVE-2026-41390

OpenClaw before 2026.3.28 contains an exec allowlist bypass vulnerability where allow-always persistence fails to unwrap /usr/bin/script and similar wrappers before storing trust decisions. Attackers can obtain user approval for one wrapped command to persist trust for wrapper binaries that execu...

7.3CVSS5.3AI score0.00026EPSS
Exploits0References3
Positive Technologies
Positive Technologies
added 2026/04/28 12:0 a.m.2 views

PT-2026-35802

OpenClaw before 2026.4.8 contains an approval-timeout fallback mechanism that bypasses strictInlineEval explicit-approval requirements on gateway and node exec hosts. Attackers can exploit this timeout fallback to execute inline eval commands that should require explicit user approval,...

7.7CVSS5.4AI score0.00054EPSS
Exploits0References6
CNNVD
CNNVD
added 2026/04/28 12:0 a.m.4 views

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.3.28 contained security vulnerabilities. These vulnerabilities stemmed from a permission bypass execution vulnerability, which allowed persistent execution of “always-always”...

7.3CVSS6AI score0.00026EPSS
Exploits0References1
RedhatCVE
RedhatCVE
added 2026/04/01 5:0 a.m.1 views

CVE-2026-30310

In its design for automatic terminal command execution, Sixth offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

9.8CVSS6AI score0.00093EPSS
Exploits0References1
EUVD
EUVD
added 2026/03/31 3:31 p.m.2 views

EUVD-2026-17410

In its design for automatic terminal command execution, Sixth offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

6AI score0.00093EPSS
Exploits0References3
NVD
NVD
added 2026/03/31 2:16 p.m.1 views

CVE-2026-30310

In its design for automatic terminal command execution, Sixth offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

9.8CVSS0.00093EPSS
Exploits0References2
RedhatCVE
RedhatCVE
added 2026/03/31 10:59 a.m.6 views

CVE-2026-30308

In its design for automatic terminal command execution, HAI Build Code Generator offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a...

9.8CVSS6AI score0.00093EPSS
Exploits0References1
RedhatCVE
RedhatCVE
added 2026/03/31 4:59 a.m.1 views

CVE-2026-30306

In its design for automatic terminal command execution, SakaDev offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

9.8CVSS6AI score0.00032EPSS
Exploits0References1
Vulnrichment
Vulnrichment
added 2026/03/31 12:0 a.m.1 views

CVE-2026-30310

In its design for automatic terminal command execution, Sixth offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

6AI score0.00093EPSS
Exploits0References2
Cvelist
Cvelist
added 2026/03/31 12:0 a.m.20 views

CVE-2026-30310

In its design for automatic terminal command execution, Sixth offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

0.00093EPSS
Exploits0References2
CVE
CVE
added 2026/03/31 12:0 a.m.2 views

CVE-2026-30310

The CVE concerns the Sixth terminal command execution design, where two options exist: execute safe commands automatically or require user approval for potentially dangerous ones. The flaw is susceptible to prompt-injection: an attacker can wrap a malicious command in a generic template and misle...

9.8CVSS6AI score0.00093EPSS
Exploits0References2
ATTACKERKB
ATTACKERKB
added 2026/03/31 12:0 a.m.1 views

CVE-2026-30310

In its design for automatic terminal command execution, Sixth offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

6AI score0.00093EPSS
Exploits0References3
Positive Technologies
Positive Technologies
added 2026/03/31 12:0 a.m.2 views

PT-2026-29351

Name of the Vulnerable Software and Affected Versions Admidio versions prior to 5.0.8 Description Admidio, a user management solution, allows attackers to bypass manual registration approval and potentially take over accounts. The create user, assign member, and assign user action modes in...

7.3CVSS5.9AI score0.00007EPSS
Exploits1References6
Positive Technologies
Positive Technologies
added 2026/03/31 12:0 a.m.1 views

PT-2026-29248

In its design for automatic terminal command execution, Sixth offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

6AI score0.00093EPSS
Exploits0References3
Rows per page
Query Builder