Lucene search
+L

111 matches found

BDU FSTEC
BDU FSTEC
added 2025/11/24 12:00 a.m.17 views

The vulnerability in the XMLToolMessage class of the langroid Python framework for application development allows a attacker to trigger a service failure or disclose protected information.

The vulnerability of the XMLToolMessage class in the langroid application development framework is related to incorrect restrictions on XML references to external objects. Exploiting this vulnerability could allow a malicious actor to cause service failures or expose sensitive information...

9.4CVSS5.8AI score0.00621EPSS
SaveExploits1References4Affected Software1
EUVD
EUVD
added 2025/10/03 8:07 p.m.12 views

EUVD-2025-15952

Malicious code in bioql PyPI...

9.8CVSS6.3AI score0.00825EPSS
SaveExploits1References4
EUVD
EUVD
added 2025/10/03 8:07 p.m.18 views

EUVD-2025-13410

Malicious code in bioql PyPI...

9.1CVSS6.3AI score0.00621EPSS
SaveExploits1References5
EUVD
EUVD
added 2025/10/03 8:07 p.m.16 views

EUVD-2025-15951

Malicious code in bioql PyPI...

9.8CVSS6.3AI score0.00531EPSS
SaveExploits0References4
Veracode
Veracode
added 2025/05/23 4:27 a.m.15 views

Arbitrary Code Execution

Langroid is vulnerable to Arbitrary Code Execution. The vulnerability is due to unsafe code evaluation due to the use of pandas.eval in the LanceDocChatAgent via the computefromdocs function, allowing attackers to execute malicious code through unsanitized input...

9.8CVSS7.3AI score0.00531EPSS
SaveExploits0References4Affected Software1
RedhatCVE
RedhatCVE
added 2025/05/22 6:16 p.m.25 views

CVE-2025-46725

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, LanceDocChatAgent uses pandas eval through computefromdocs. As a result, an attacker may be able to make the agent run malicious commands through QueryPlan.dataframecalc compromising t...

9.8CVSS7AI score0.00531EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/22 6:16 p.m.10 views

CVE-2025-46724

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, TableChatAgent uses pandas eval. If fed by untrusted user input, like the case of a public-facing LLM application, it may be vulnerable to code injection. Langroid 0.53.15 sanitizes...

9.8CVSS7.3AI score0.00825EPSS
SaveExploits1References1
NVD
NVD
added 2025/05/20 6:15 p.m.28 views

CVE-2025-46724

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, TableChatAgent uses pandas eval. If fed by untrusted user input, like the case of a public-facing LLM application, it may be vulnerable to code injection. Langroid 0.53.15 sanitizes...

9.8CVSS0.00825EPSS
SaveExploits1References2
NVD
NVD
added 2025/05/20 6:15 p.m.51 views

CVE-2025-46725

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, LanceDocChatAgent uses pandas eval through computefromdocs. As a result, an attacker may be able to make the agent run malicious commands through QueryPlan.dataframecalc compromising t...

9.8CVSS0.00531EPSS
SaveExploits0References2
Snyk
Snyk
added 2025/05/20 5:49 p.m.5 views

Arbitrary Code Injection

Overview langroid is a Harness LLMs with Multi-Agent Programming Affected versions of this package are vulnerable to Arbitrary Code Injection through the computefromdocs process. An attacker can execute arbitrary code by manipulating the input data to the QueryPlan.dataframecalc method. Remediati...

9.8CVSS8.1AI score0.00531EPSS
SaveExploits0References2
Snyk
Snyk
added 2025/05/20 5:49 p.m.3 views

Arbitrary Code Injection

Overview langroid is a Harness LLMs with Multi-Agent Programming Affected versions of this package are vulnerable to Arbitrary Code Injection due to the use of pandas eval function. An attacker can execute arbitrary code by supplying malicious input to this function. This is only exploitable if t...

9.8CVSS8.1AI score0.00825EPSS
SaveExploits1References2
Vulnrichment
Vulnrichment
added 2025/05/20 5:24 p.m.8 views

CVE-2025-46725 Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, LanceDocChatAgent uses pandas eval through computefromdocs. As a result, an attacker may be able to make the agent run malicious commands through QueryPlan.dataframecalc compromising t...

9.3CVSS6.6AI score0.00531EPSS
SaveExploits0References2
OSV
OSV
added 2025/05/20 5:24 p.m.23 views

CVE-2025-46725 Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, LanceDocChatAgent uses pandas eval through computefromdocs. As a result, an attacker may be able to make the agent run malicious commands through QueryPlan.dataframecalc compromising t...

9.3CVSS6.8AI score
SaveExploits0References4
Cvelist
Cvelist
added 2025/05/20 5:24 p.m.69 views

CVE-2025-46725 Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, LanceDocChatAgent uses pandas eval through computefromdocs. As a result, an attacker may be able to make the agent run malicious commands through QueryPlan.dataframecalc compromising t...

9.3CVSS0.00531EPSS
SaveExploits0References2
CVE
CVE
added 2025/05/20 5:24 p.m.69 views

CVE-2025-46725

Langroid (Python framework for LLM-powered apps) contains a code execution vulnerability in the LanceDocChatAgent prior to version 0.53.15, caused by the use of pandas.eval() in the compute_from_docs() path. An attacker could cause the agent to execute malicious commands via crafted input and rel...

9.8CVSS6.6AI score0.00531EPSS
SaveExploits0References2Affected Software1
Vulnrichment
Vulnrichment
added 2025/05/20 5:22 p.m.7 views

CVE-2025-46724 Langroid has a Code Injection vulnerability in TableChatAgent

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, TableChatAgent uses pandas eval. If fed by untrusted user input, like the case of a public-facing LLM application, it may be vulnerable to code injection. Langroid 0.53.15 sanitizes...

9.8CVSS9.7AI score0.00825EPSS
SaveExploits1References2
Cvelist
Cvelist
added 2025/05/20 5:22 p.m.38 views

CVE-2025-46724 Langroid has a Code Injection vulnerability in TableChatAgent

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, TableChatAgent uses pandas eval. If fed by untrusted user input, like the case of a public-facing LLM application, it may be vulnerable to code injection. Langroid 0.53.15 sanitizes...

9.8CVSS0.00825EPSS
SaveExploits1References2
CVE
CVE
added 2025/05/20 5:22 p.m.92 views

CVE-2025-46724

Langroid CVE-2025-46724 affects TableChatAgent, where untrusted input can trigger code injection via pandas_eval in TableChatAgent prior to v0.53.15. The project added a WAF in pandas_utils.py and warnings, with a patch in v0.59.32 that blocks the bypass. However, subsequent disclosures (CVE-2026...

9.8CVSS9.7AI score0.00825EPSS
SaveExploits1References2Affected Software1
OSV
OSV
added 2025/05/20 5:22 p.m.12 views

CVE-2025-46724 Langroid has a Code Injection vulnerability in TableChatAgent

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, TableChatAgent uses pandas eval. If fed by untrusted user input, like the case of a public-facing LLM application, it may be vulnerable to code injection. Langroid 0.53.15 sanitizes...

9.8CVSS6.8AI score
SaveExploits0References4
Positive Technologies
Positive Technologies
added 2025/05/20 12:00 a.m.10 views

PT-2025-22276

Name of the Vulnerable Software and Affected Versions Langroid versions prior to 0.53.15 Description The issue concerns Langroid, a Python framework for building large language model LLM-powered applications. In versions prior to 0.53.15, the TableChatAgent uses pandas eval, which may be vulnerab...

9.8CVSS5.5AI score0.00825EPSS
SaveExploits1References17
Rows per page
Query Builder