Lucene search
+L

36 matches found

Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/08/04 12:00 a.m.•11 views

CVE-2026-70477: Improper Control of Generation of Code

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, a prompt injection sent to a chatflow using a CSV Agent node can cause the LLM to respond with a malicious Python script that bypasses the blocklist validator and executes in an unsandboxed...

9.8CVSS9.2AI score0.00814EPSS
SaveExploits0References6
osv_mal
osv_mal
•added 2026/07/29 8:55 p.m.•23 views

MAL-2026-11171 Malicious code in @ai-agent-node/agent-node (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 8edd22e8454df2a9c10d47ea5c39560f9384598e7fb2a26b26b8f647fd5d2dd1 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

5.9AI score
SaveExploits0References1
osv_mal
osv_mal
•added 2026/07/29 8:55 p.m.•30 views

MAL-2026-11173 Malicious code in @ai-agent-node/nodesql (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 9bd9860fa6b32249720b90f9ba4f48642cbd746fe04e701b05cba6eef2951671 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

5.9AI score
SaveExploits0References1
osv_mal
osv_mal
•added 2026/07/29 8:55 p.m.•28 views

MAL-2026-11172 Malicious code in @ai-agent-node/createnode (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 88461b4fe3bc4e6e16f6dbabec2dd4acdf4eb2df6390170776629e5f955f13f4 @ai-agent-node/createnode ships a 12-line main module that, on require, fetches https://api.github.com/gists/198a0bbec7a6018e9250615d26e37b90 owner:...

5.7AI score
SaveExploits0References3
OSSF Malicious Packages
OSSF Malicious Packages
•added 2026/07/29 8:55 p.m.•43 views

Malicious code in @ai-agent-node/createnode (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 88461b4fe3bc4e6e16f6dbabec2dd4acdf4eb2df6390170776629e5f955f13f4 @ai-agent-node/createnode ships a 12-line main module that, on require, fetches https://api.github.com/gists/198a0bbec7a6018e9250615d26e37b90 owner:...

5.7AI score
SaveExploits0References3
OSSF Malicious Packages
OSSF Malicious Packages
•added 2026/07/29 8:55 p.m.•33 views

Malicious code in @ai-agent-node/agent-node (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 8edd22e8454df2a9c10d47ea5c39560f9384598e7fb2a26b26b8f647fd5d2dd1 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

5.9AI score
SaveExploits0References1
Github Security Blog
Github Security Blog
•added 2026/07/29 8:55 p.m.•7 views

Malware in @ai-agent-node/agent-node

Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be rotated immediately from a different computer. The package should be removed, but as full control of the computer may have been given to an outsid...

5.8AI score
SaveExploits0References1Affected Software1
Github Security Blog
Github Security Blog
•added 2026/07/29 8:55 p.m.•7 views

Malware in @ai-agent-node/nodesql

Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be rotated immediately from a different computer. The package should be removed, but as full control of the computer may have been given to an outsid...

5.8AI score
SaveExploits0References1Affected Software1
Github Security Blog
Github Security Blog
•added 2026/07/29 8:55 p.m.•8 views

Malware in @ai-agent-node/createnode

Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be rotated immediately from a different computer. The package should be removed, but as full control of the computer may have been given to an outsid...

5.8AI score
SaveExploits0References1Affected Software1
CVE
CVE
•added 2026/07/02 7:38 p.m.•63 views

CVE-2026-58579

RAGFlow before 0.26.3 stores an agent pipeline (DSL) node name without sanitization. The update endpoint normalizes DSL via JSON serialization but preserves the node name, and the dataflow-result UI renders it with dangerouslySetInnerHTML while i18next escapeValue is false, allowing an authentica...

5.4CVSS6AI score0.00298EPSS
SaveExploits0References5
Positive Technologies
Positive Technologies
•added 2026/04/21 12:00 a.m.•32 views

PT-2026-34236

Name of the Vulnerable Software and Affected Versions Flowise versions prior to 3.1.0 Description A flaw exists in the run method of the CSV Agents class due to improper sandboxing when evaluating Python scripts generated by a Large Language Model LLM. An unauthenticated attacker can use prompt...

9.8CVSS8.5AI score0.01789EPSS
SaveExploits5References14
Mend
Mend
•added 2026/02/26 1:55 a.m.•12 views

CVE-2026-27966

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.8.0, the CSV Agent node in Langflow hardcodes "allowdangerouscode=True", which automatically exposes LangChain’s Python REPL tool "pythonreplast". As a result, an attacker can execute arbitrary Pytho...

9.8CVSS8.8AI score0.35246EPSS
SaveExploits6References7
osv_cve
osv_cve
•added 2026/02/26 1:55 a.m.•29 views

CVE-2026-27966 Langflow has Remote Code Execution in CSV Agent

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.8.0, the CSV Agent node in Langflow hardcodes allowdangerouscode=True, which automatically exposes LangChain’s Python REPL tool pythonreplast. As a result, an attacker can execute arbitrary Python an...

9.8CVSS8.8AI score0.35246EPSS
SaveExploits6References4
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/02/26 12:00 a.m.•11 views

CVE-2026-27966: Improper Control of Generation of Code

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.8.0, the CSV Agent node in Langflow hardcodes allowdangerouscode=True, which automatically exposes LangChain’s Python REPL tool pythonreplast. As a result, an attacker can execute arbitrary Python an...

9.8CVSS9AI score0.35246EPSS
SaveExploits6References1
Positive Technologies
Positive Technologies
•added 2026/02/26 12:00 a.m.•42 views

PT-2026-22107

Name of the Vulnerable Software and Affected Versions Langflow versions prior to 1.8.0 Description Langflow is a tool for building and deploying AI-powered agents and workflows. In the CSV Agent node, the variable allow dangerous code is hardcoded to True, which automatically exposes LangChain's...

9.8CVSS9AI score0.35246EPSS
SaveExploits6References27
osv_mal
osv_mal
•added 2025/08/23 2:33 p.m.•13 views

MAL-2025-41309 Malicious code in montage-agent (npm)

--- -= Per source details. Do not edit below this line.=- Source: ossf-package-analysis 285d4d62fe8147f0b104cedb1c1bc54ecc1a11483fb2240f89369ddd2de3b7d3 The OpenSSF Package Analysis project identified 'montage-agent' @ 99.0.9 npm as malicious. It is considered malicious because: - The package...

7.3AI score
SaveExploits0
Rows per page
Query Builder