Lucene search
+L

27 matches found

NVD
NVD
•added 2026/08/06 1:16 a.m.•12 views

CVE-2026-18974

A vulnerability was found in heshengtao super-agent-party up to 0.4.1. This affects the function getfilecontent of the file server.py of the component executetoolmanually Endpoint. The manipulation of the argument toolname/toolparams results in information disclosure. The attack can be launched...

6.9CVSS0.00532EPSS
SaveExploits0References6
EUVD
EUVD
•added 2026/08/06 12:45 a.m.•20 views

EUVD-2026-53695

A vulnerability was found in heshengtao super-agent-party up to 0.4.1. This affects the function getfilecontent of the file server.py of the component executetoolmanually Endpoint. The manipulation of the argument toolname/toolparams results in information disclosure. The attack can be launched...

6.9CVSS5.1AI score0.00532EPSS
SaveExploits0References6
CVE
CVE
•added 2026/07/15 11:25 a.m.•26 views

CVE-2026-60087

PRAISONAI v1.6.78 and earlier are affected: PraisonAI caches tool approvals by tool name, enabling reuse of initial approvals for subsequent calls with arbitrary arguments. This can allow an attacker to obtain approval for a benign operation and then execute dangerous file write operations within...

6.9CVSS6.2AI score0.00148EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/07/13 12:00 a.m.•15 views

PT-2026-59578

Summary The approval system in PraisonAI Agents caches tool approval decisions by tool name only, not by invocation arguments. Once a user approves execute command for any command e.g., ls -la, all subsequent execute command calls in that execution context bypass the approval prompt entirely...

6.8CVSS6.3AI score0.00166EPSS
SaveExploits0References8
EUVD
EUVD
•added 2026/06/19 12:31 a.m.•19 views

EUVD-2026-37958

PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent executecommand calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and...

6.8CVSS5.3AI score0.00166EPSS
SaveExploits0References3
NVD
NVD
•added 2026/06/18 11:16 p.m.•24 views

CVE-2026-56074

PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent executecommand calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and...

6.8CVSS0.00166EPSS
SaveExploits0References2
attackerkb
attackerkb
•added 2026/06/18 10:12 p.m.•13 views

CVE-2026-56074

PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent executecommand calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and...

6.8CVSS5.3AI score0.00166EPSS
SaveExploits0References3
Positive Technologies
Positive Technologies
•added 2026/05/13 12:00 a.m.•37 views

PT-2026-40787

Three CVEs CVE-2026-29774, CVE-2026-30015, CVE-2026-30221 exploited the fact that the protocol did not, in version 1.2, canonicalize tool names. Multiple servers in the same session could expose tools named, respectively: readfile the legitimate filesystem server…...

8.2CVSS5.8AI score0.00486EPSS
SaveExploits1References1
Positive Technologies
Positive Technologies
•added 2026/05/13 12:00 a.m.•23 views

PT-2026-40788

Three CVEs CVE-2026-29774, CVE-2026-30015, CVE-2026-30221 exploited the fact that the protocol did not, in version 1.2, canonicalize tool names. Multiple servers in the same session could expose tools named, respectively: readfile the legitimate filesystem server…...

8.2CVSS5.8AI score0.00486EPSS
SaveExploits1References1
NVD
NVD
•added 2026/05/08 2:16 p.m.•41 views

CVE-2026-44339

PraisonAI is a multi-agent teams system. Prior to praisonai version 4.6.37 and praisonaiagents version 1.6.37, praisonaiagents resolves unresolved tool names against module globals and main after it fails to match the declared tool list and the registry. With the default agent configuration,...

8.6CVSS0.00427EPSS
SaveExploits1References1
OSV
OSV
•added 2026/05/08 1:37 p.m.•14 views

CVE-2026-44339 PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute

PraisonAI is a multi-agent teams system. Prior to praisonai version 4.6.37 and praisonaiagents version 1.6.37, praisonaiagents resolves unresolved tool names against module globals and main after it fails to match the declared tool list and the registry. With the default agent configuration,...

8.6CVSS5.9AI score
SaveExploits0References3
CNNVD
CNNVD
•added 2026/05/08 12:00 a.m.•27 views

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 4.6.37 and PraisonAIagents prior to 1.6.37 have security vulnerabilities. These vulnerabilities stem from unresolved tool name resolution issues, which may allow attackers to...

8.6CVSS5.8AI score0.00427EPSS
SaveExploits1References1
Positive Technologies
Positive Technologies
•added 2026/04/10 12:00 a.m.•39 views

PT-2026-50805

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 1.5.128 Description The software caches tool approval decisions based solely on the tool name rather than the invocation arguments. This allows subsequent calls to the execute command function to bypass approval...

6.8CVSS6AI score0.00166EPSS
SaveExploits0References16
SUSE CVE
SUSE CVE
•added 2026/03/25 12:25 a.m.•13 views

SUSE CVE-2026-30856

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming...

7.6CVSS6.1AI score0.00291EPSS
SaveExploits1References3
RedhatCVE
RedhatCVE
•added 2026/03/09 8:02 a.m.•10 views

CVE-2026-30856

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming...

5.9CVSS5.9AI score0.00291EPSS
SaveExploits1References1
NVD
NVD
•added 2026/03/07 5:15 p.m.•15 views

CVE-2026-30856

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming...

7.6CVSS0.00291EPSS
SaveExploits1References1
CVE
CVE
•added 2026/03/07 4:32 p.m.•74 views

CVE-2026-30856

WeKnora CVE-2026-30856: Pre-0.3.0 versions are vulnerable to a tool-name collision and indirect prompt injection via an MCP client naming convention (mcp_{service}_{tool}), allowing a remote MCP server to hijack tool execution and potentially exfiltrate prompts/context or run other tools with use...

7.6CVSS5.9AI score0.00291EPSS
SaveExploits1References1Affected Software1
attackerkb
attackerkb
•added 2026/03/07 4:32 p.m.•8 views

CVE-2026-30856

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming...

5.9CVSS5.9AI score0.00291EPSS
SaveExploits1References2Affected Software1
CNNVD
CNNVD
•added 2026/03/07 12:00 a.m.•16 views

WeKnora 安全漏洞

WeKnora is an open-source framework based on LLM developed by Tencent. It features deep document understanding using the RAG paradigm, semantic retrieval, and context-aware answers. Prior to version 0.3.0, WeKnora had security vulnerabilities. These vulnerabilities were caused by tool name...

7.6CVSS7.4AI score0.00291EPSS
SaveExploits1References2
Snyk
Snyk
•added 2026/03/06 11:54 p.m.•6 views

Use of Incorrectly-Resolved Name or Reference

Overview Affected versions of this package are vulnerable to Use of Incorrectly-Resolved Name or Reference via the MCPTool.Name sanitization in the NewMCPTool registration process in internal/agent/tools. An attacker can execute arbitrary MCP tools and inject prompts to exfiltrate context by...

7.6CVSS6AI score0.00291EPSS
SaveExploits1References2
Rows per page
Query Builder