Lucene search
K

427 matches found

RedhatCVE
RedhatCVE
added 2026/06/05 7:12 p.m.6 views

CVE-2026-39891

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user input from agent.start is passed directly into these tools without escaping, template expressions in the...

8.8CVSS5.5AI score0.00558EPSS
Exploits1References1
RedhatCVE
RedhatCVE
added 2026/06/05 7:12 p.m.6 views

CVE-2026-44335

PraisonAI is a multi-agent teams system. Prior to version 1.6.32, the URL checking logic in PraisonAI has a logical flaw that could be bypassed by attackers, leading to SSRF attacks. This issue has been patched in version 1.6.32...

9.8CVSS5.3AI score0.00378EPSS
Exploits1References1
RedhatCVE
RedhatCVE
added 2026/06/05 7:12 p.m.8 views

CVE-2026-44340

PraisonAI is a multi-agent teams system. Prior to version 4.6.37, the safeextractall helper that all recipe pull, recipe publish, and recipe unpack flows route through validates each archive member's name for absolute paths, .. segments, and resolved-path escape — but does not validate...

8.7CVSS5.5AI score0.00433EPSS
Exploits1References1
RedhatCVE
RedhatCVE
added 2026/06/05 7:12 p.m.6 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,...

8.6CVSS5.4AI score0.00363EPSS
Exploits1References1
OSV
OSV
added 2026/05/29 10:42 p.m.6 views

GHSA-3QG8-5G3R-79V5 praisonai-platform: JWT signing key defaults to hardcoded "dev-secret-change-me", allowing token forgery for any user when PLATFORM_ENV is unset

Summary Type: Insecure default cryptographic key. The JWT signing secret defaults to the hardcoded literal "dev-secret-change-me" when PLATFORMJWTSECRET is unset. A safety check exists but only fires when PLATFORMENV != "dev"; the default value of PLATFORMENV is "dev", so the check is silently...

9.8CVSS6AI score0.00054EPSS
Exploits0References2
OSV
OSV
added 2026/05/29 10:42 p.m.6 views

GHSA-H37G-4H4P-9X97 PraisonAI Platform: Missing role checks let any workspace member become owner and control workspace membership

Summary PraisonAI Platform has a broken workspace authorization check that allows any authenticated low-privilege workspace member to escalate their own role to owner. The issue is caused by privileged workspace-management routes using the shared dependency requireworkspacemember... without...

8.8CVSS5.8AI score0.00063EPSS
Exploits0References2
OSV
OSV
added 2026/05/29 10:31 p.m.6 views

GHSA-HVHP-V2GC-268Q PraisonAI has an Arbitrary File Write in Python API

Bug Report: Arbitrary File Write in Python API Summary Hidden metadata in a webpage causes PraisonAI agents to write attacker-controlled content to arbitrary paths. writefile skips path validation when workspace=None always None in production. Affected PraisonAI outputfile: /tmp/flag.txt...

7.1CVSS6AI score0.00051EPSS
Exploits0References2
Github Security Blog
Github Security Blog
added 2026/05/29 10:31 p.m.21 views

PraisonAI has an Arbitrary File Write in Python API

Bug Report: Arbitrary File Write in Python API Summary Hidden metadata in a webpage causes PraisonAI agents to write attacker-controlled content to arbitrary paths. writefile skips path validation when workspace=None always None in production. Affected PraisonAI outputfile: /tmp/flag.txt...

6AI score0.00051EPSS
Exploits0References2Affected Software1
Snyk
Snyk
added 2026/05/29 10:30 p.m.5 views

Missing 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...

8.7CVSS5.5AI score0.00075EPSS
Exploits0References3
Snyk
Snyk
added 2026/05/29 10:30 p.m.6 views

Protection Mechanism Failure

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...

9.9CVSS5.9AI score0.0012EPSS
Exploits0References3
Snyk
Snyk
added 2026/05/29 10:29 p.m.5 views

Exposure of Sensitive System Information to an Unauthorized Control Sphere

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...

6.9CVSS5.5AI score0.00014EPSS
Exploits0References2
OSV
OSV
added 2026/05/29 10:29 p.m.6 views

GHSA-8444-4FHQ-FXPQ PraisonAI `deploy --type api` emits a Flask server with authentication disabled by default

Summary CVE-2026-44338 GHSA-6rmh-7xcm-cpxj documents that PraisonAI ships a code-generator praisonai.deploy.api.generateapiservercode that emits a Flask API server with authentication disabled by default. Users who follow the documented quickstart praisonai deploy --type api get a server that: -...

9.8CVSS6AI score0.0008EPSS
Exploits0References3
Github Security Blog
Github Security Blog
added 2026/05/29 10:29 p.m.24 views

PraisonAI `deploy --type api` emits a Flask server with authentication disabled by default

Summary CVE-2026-44338 GHSA-6rmh-7xcm-cpxj documents that PraisonAI ships a code-generator praisonai.deploy.api.generateapiservercode that emits a Flask API server with authentication disabled by default. Users who follow the documented quickstart praisonai deploy --type api get a server that: -...

7.3CVSS6.2AI score0.19037EPSS
Exploits3References3Affected Software1
OSV
OSV
added 2026/05/29 10:27 p.m.6 views

GHSA-86QC-R5V2-V6X6 PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset

Summary PraisonAI's call server exposes a network-facing agent control API without authentication when CALLSERVERTOKEN is not configured. The affected component is the praisonai.api.agentinvoke router as mounted by praisonai.api.call. The authentication helper verifytoken fails open when...

9.8CVSS5.8AI score0.00075EPSS
Exploits0References2
Github Security Blog
Github Security Blog
added 2026/05/29 10:27 p.m.21 views

PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset

Summary PraisonAI's call server exposes a network-facing agent control API without authentication when CALLSERVERTOKEN is not configured. The affected component is the praisonai.api.agentinvoke router as mounted by praisonai.api.call. The authentication helper verifytoken fails open when...

5.8AI score0.00075EPSS
Exploits0References2Affected Software1
Snyk
Snyk
added 2026/05/29 10:27 p.m.5 views

Server-side Request Forgery (SSRF)

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via improper URL validation the spidertools component. An attacker can access internal loopback-only HTTP...

6.9CVSS5.5AI score0.00014EPSS
Exploits0References2
OSV
OSV
added 2026/05/29 10:26 p.m.5 views

GHSA-78R8-WWQV-R299 PraisonAI: Arbitrary code execution via unguarded `spec.loader.exec_module` in `agents_generator.py` - sibling of CVE-2026-44334

Arbitrary code execution via ungated spec.loader.execmodule in agentsgenerator.py v4.6.32 chokepoint refactor bypass Summary The v4.6.32 chokepoint refactor which patched CVE-2026-44334 / GHSA-xcmw-grxf-wjhj added the PRAISONAIALLOWLOCALTOOLS env-var gate to the tooloverride.py sinks. However, tw...

8.1CVSS6.4AI score0.00102EPSS
Exploits0References2
Snyk
Snyk
added 2026/05/29 10:26 p.m.5 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...

6.8CVSS6AI score0.00102EPSS
Exploits0References3
Positive Technologies
Positive Technologies
added 2026/05/29 12:0 a.m.8 views

PT-2026-45050

Summary The first-party PraisonAI A2A server example combines three behaviors into a remotely exploitable Critical chain: 1. The example exposes an A2A server without configuring auth token. 2. The same example binds the server to 0.0.0.0. 3. The example registers a calculateexpression tool...

9.8CVSS6.3AI score0.00084EPSS
Exploits0References3
Positive Technologies
Positive Technologies
added 2026/05/29 12:0 a.m.7 views

PT-2026-45056

Bug Report: Arbitrary File Write in Python API Summary Hidden metadata in a webpage causes PraisonAI agents to write attacker-controlled content to arbitrary paths. write file skips path validation when workspace=None always None in production. Affected PraisonAI output file: /tmp/flag.txt output...

7.1CVSS6AI score0.00051EPSS
Exploits0References3
Rows per page
Query Builder