Lucene search
+L

796 matches found

OSV
OSV
added 2026/04/10 7:32 p.m.4 views

GHSA-G985-WJH9-QXXC PraisonAI Vulnerable to RCE via Automatic tools.py Import

PraisonAI automatically imports ./tools.py from the current working directory when launching certain components. This includes call.py, toolresolver.py, and CLI tool-loading paths. A malicious tools.py placed in the process working directory is executed immediately, allowing arbitrary Python code...

8.4CVSS6.4AI score0.00246EPSS
SaveExploits1References4
Github Security Blog
Github Security Blog
added 2026/04/10 7:32 p.m.10 views

PraisonAI Vulnerable to RCE via Automatic tools.py Import

PraisonAI automatically imports ./tools.py from the current working directory when launching certain components. This includes call.py, toolresolver.py, and CLI tool-loading paths. A malicious tools.py placed in the process working directory is executed immediately, allowing arbitrary Python code...

8.4CVSS6.4AI score0.00246EPSS
SaveExploits1References4Affected Software2
Snyk
Snyk
added 2026/04/10 7:32 p.m.5 views

SQL Injection

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

9.8CVSS6AI score0.00297EPSS
SaveExploits1References2
Snyk
Snyk
added 2026/04/10 7:28 p.m.9 views

Permissive Cross-domain Policy with Untrusted Domains

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

8.6CVSS6AI score0.00743EPSS
SaveExploits0References2
EUVD
EUVD
added 2026/04/10 7:28 p.m.6 views

EUVD-2026-21511

PraisonAI Vulnerable to Sensitive Environment Variable Exposure via Untrusted MCP Subprocess Execution...

5.5CVSS5.8AI score0.00182EPSS
SaveExploits0References3
OSV
OSV
added 2026/04/10 7:28 p.m.21 views

GHSA-PJ2R-F9MW-VRCQ PraisonAI Vulnerable to Sensitive Environment Variable Exposure via Untrusted MCP Subprocess Execution

PraisonAI’s MCP Model Context Protocol integration allows spawning background servers via stdio using user-supplied command strings e.g., MCP"npx -y @smithery/cli ...". These commands are executed through Python’s subprocess module. By default, the implementation forwards the entire parent proces...

5.5CVSS6.1AI score0.00182EPSS
SaveExploits0References4
Snyk
Snyk
added 2026/04/10 7:27 p.m.7 views

Directory Traversal

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

9.6CVSS6.3AI score0.00379EPSS
SaveExploits1References2
EUVD
EUVD
added 2026/04/10 7:27 p.m.5 views

EUVD-2026-21509

PraisonAI vulnerable to arbitrary file write via path traversal in praisonai recipe unpack...

9.4CVSS5.9AI score0.00379EPSS
SaveExploits1References3
EUVD
EUVD
added 2026/04/10 7:26 p.m.6 views

EUVD-2026-21508

PraisonAI Vulnerable to Implicit Execution of Arbitrary Code via Automatic tools.py Loading...

7.8CVSS5.8AI score0.00209EPSS
SaveExploits0References3
EUVD
EUVD
added 2026/04/10 7:26 p.m.6 views

EUVD-2026-21166

PraisonAI Vulnerable to Decompression Bomb DoS via Recipe Bundle Extraction Without Size Limits...

6.5CVSS5.8AI score0.00243EPSS
SaveExploits1References3
Snyk
Snyk
added 2026/04/10 7:26 p.m.8 views

Improper Handling of Highly Compressed Data (Data Amplification)

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

7.1CVSS5.8AI score0.00243EPSS
SaveExploits1References2
OSV
OSV
added 2026/04/10 7:26 p.m.6 views

GHSA-F2H6-7XFR-XM8W PraisonAI Vulnerable to Decompression Bomb DoS via Recipe Bundle Extraction Without Size Limits

Summary The safeextractall function in PraisonAI's recipe registry validates archive members against path traversal attacks but performs no checks on individual member sizes, cumulative extracted size, or member count before calling tar.extractall. An attacker can publish a malicious recipe bundl...

6.5CVSS5.9AI score0.00243EPSS
SaveExploits1References4
Snyk
Snyk
added 2026/04/10 7:26 p.m.6 views

Unsafe Dependency Resolution

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

9.6CVSS6.1AI score0.00304EPSS
SaveExploits1References2
EUVD
EUVD
added 2026/04/10 7:26 p.m.7 views

EUVD-2026-21212

PraisonAI Vulnerable Untrusted Remote Template Code Execution...

9.3CVSS5.8AI score0.00304EPSS
SaveExploits1References3
Snyk
Snyk
added 2026/04/10 7:25 p.m.4 views

Incorrect Authorization

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

8.8CVSS6AI score0.00707EPSS
SaveExploits0References2
EUVD
EUVD
added 2026/04/10 7:25 p.m.6 views

EUVD-2026-21510

PraisonAI Vulnerable to Code Injection and Protection Mechanism Failure...

8.6CVSS5.8AI score0.0024EPSS
SaveExploits1References3
OSV
OSV
added 2026/04/10 7:25 p.m.4 views

GHSA-3C4R-6P77-XWR7 PraisonAI Vulnerable to Code Injection and Protection Mechanism Failure

PraisonAI's AST-based Python sandbox can be bypassed using type.getattribute trampoline, allowing arbitrary code execution when running untrusted agent code. Description The executecodedirect function in praisonaiagents/tools/pythontools.py uses AST filtering to block dangerous Python attributes...

8.6CVSS6.5AI score0.0024EPSS
SaveExploits1References4
Snyk
Snyk
added 2026/04/10 7:24 p.m.7 views

Exposure of Sensitive Information Through Environmental Variables

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

7.4CVSS5.9AI score0.00273EPSS
SaveExploits1References2
Snyk
Snyk
added 2026/04/10 7:24 p.m.5 views

Declaration of Catch for Generic Exception

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

7.9CVSS5.8AI score0.00227EPSS
SaveExploits1References3
EUVD
EUVD
added 2026/04/10 7:23 p.m.7 views

EUVD-2026-21170

PraisonAIAgents has SSRF and Local File Read via Unvalidated URLs in webcrawl Tool...

7.7CVSS5.8AI score0.00269EPSS
SaveExploits1References2
Rows per page
Query Builder