Lucene search
K

438 matches found

Nuclei
Nuclei
added yesterday9 views

PraisonAI - Authentication Bypass

PraisonAI 2.5.6 to 4.6.34 contains a broken authentication caused by disabled default authentication in legacy Flask API server, letting remote attackers access /agents and trigger workflows without token, exploit requires network access to API server. id: CVE-2026-44338 info: name: PraisonAI -...

7.3CVSS6.2AI score0.19037EPSS
Exploits3References2
EUVD
EUVD
added 4 days ago9 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 score
Exploits0References3
EUVD
EUVD
added 4 days ago6 views

EUVD-2026-37961

PraisonAI before 1.5.115 contains an information disclosure vulnerability in the MultiAgentLedger component that allows attackers to access sensitive data by registering agents with duplicate IDs. Attackers can exploit the lack of agent ID uniqueness enforcement to share ledger instances and expo...

7.1CVSS5.2AI score
Exploits0References4
Github Security Blog
Github Security Blog
added 4 days ago4 views

Duplicate Advisory: PraisonAI has Memory State Leakage and Path Traversal in MultiAgent Context Handling

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-766v-q9x3-g744. This link is maintained to preserve external references. Original Description PraisonAI before 1.5.115 contains a path traversal vulnerability in MultiAgentMonitor that fails to sanitize agent ID...

8.8CVSS6AI score
Exploits0References5Affected Software1
Github Security Blog
Github Security Blog
added 4 days ago5 views

Duplicate Advisory: PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell Commands

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-ffp3-3562-8cv3. This link is maintained to preserve external references. Original Description PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing...

6.8CVSS5.8AI score
Exploits0References4Affected Software1
NVD
NVD
added 5 days ago11 views

CVE-2026-56075

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approvalmode to auto, overriding administrator configuration from PRAISONAPPROVALMODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary...

8.8CVSS
Exploits0References2
NVD
NVD
added 5 days ago11 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...

6.8CVSS
Exploits0References2
NVD
NVD
added 5 days ago10 views

CVE-2026-56076

PraisonAI before 1.5.128 contains a cross-origin agent execution vulnerability in the AGUI endpoint that allows remote attackers to trigger arbitrary agent execution. The POST /agui endpoint lacks authentication and hardcodes Access-Control-Allow-Origin: headers, combined with Starlette's...

8.6CVSS
Exploits0References2
NVD
NVD
added 5 days ago11 views

CVE-2026-56078

PraisonAI before 1.5.115 contains a path traversal vulnerability in MultiAgentMonitor that fails to sanitize agent IDs when building file paths. Attackers can include traversal sequences like ../ in agent IDs to read, write, or overwrite arbitrary files, enabling sensitive disclosure, denial of...

8.8CVSS
Exploits0References3
NVD
NVD
added 5 days ago9 views

CVE-2026-56077

PraisonAI before 1.5.115 contains an information disclosure vulnerability in the MultiAgentLedger component that allows attackers to access sensitive data by registering agents with duplicate IDs. Attackers can exploit the lack of agent ID uniqueness enforcement to share ledger instances and expo...

7.1CVSS
Exploits0References3
CVE
CVE
added 5 days ago17 views

CVE-2026-56078

CVE-2026-56078 affects PraisonAI prior to 1.5.115, specifically a path traversal vulnerability in the MultiAgentMonitor component. The issue arises because agent IDs are not properly sanitized when building file paths, allowing an attacker to inject traversal sequences (e.g., ../) to access arbit...

8.8CVSS5.6AI score
Exploits0References3
Cvelist
Cvelist
added 5 days ago15 views

CVE-2026-56078 PraisonAI - Arbitrary File Read and Write via Path Traversal in MultiAgentMonitor

PraisonAI before 1.5.115 contains a path traversal vulnerability in MultiAgentMonitor that fails to sanitize agent IDs when building file paths. Attackers can include traversal sequences like ../ in agent IDs to read, write, or overwrite arbitrary files, enabling sensitive disclosure, denial of...

8.8CVSS
Exploits0References3
CVE
CVE
added 5 days ago16 views

CVE-2026-56077

CVE-2026-56077 concerns PraisonAI before 1.5.115, where an information disclosure vulnerability exists in the MultiAgentLedger component. The root cause is failure to enforce unique agent IDs during registration, enabling attackers to share ledger instances and access sensitive data including sys...

7.1CVSS5.2AI score
Exploits0References3
CVE
CVE
added 5 days ago13 views

CVE-2026-56076

PrajionAI CVE-2026-56076 affects PraisonAI before 1.5.128. The vulnerability is a cross-origin agent execution via the AGUI endpoint (/agui): the endpoint lacks authentication and returns a wildcard CORS header (Access-Control-Allow-Origin: *). Combined with Starlette’s Content-Type-agnostic JSON...

8.6CVSS5.8AI score
Exploits0References2
Cvelist
Cvelist
added 5 days ago15 views

CVE-2026-56076 PraisonAI - Cross-Origin Agent Execution via Hardcoded Wildcard CORS and Missing Authentication on AGUI Endpoint

PraisonAI before 1.5.128 contains a cross-origin agent execution vulnerability in the AGUI endpoint that allows remote attackers to trigger arbitrary agent execution. The POST /agui endpoint lacks authentication and hardcodes Access-Control-Allow-Origin: headers, combined with Starlette's...

8.6CVSS
Exploits0References2
CVE
CVE
added 5 days ago20 views

CVE-2026-56075

PrasionAI before 4.5.128 contains an arbitrary shell command execution vulnerability in which UI modules hardcode approval_mode to auto, overriding the PRAISON_APPROVAL_MODE environment variable. This allows authenticated attackers to instruct the LLM agent to run arbitrary commands via subproces...

8.8CVSS6AI score
Exploits0References2
Cvelist
Cvelist
added 5 days ago19 views

CVE-2026-56075 PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approvalmode to auto, overriding administrator configuration from PRAISONAPPROVALMODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary...

8.8CVSS
Exploits0References2
Cvelist
Cvelist
added 5 days ago15 views

CVE-2026-56074 PraisonAI - Tool Approval Cache Bypass via Coarse-Grained Caching

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...

6.8CVSS
Exploits0References2
Positive Technologies
Positive Technologies
added 5 days ago9 views

PT-2026-50807

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 1.5.128 Description A cross-origin agent execution issue exists in the 'POST /agui' endpoint, allowing remote attackers to trigger arbitrary agent execution. The endpoint lacks authentication and utilizes hardcoded...

8.6CVSS6.2AI score
Exploits0References5
Positive Technologies
Positive Technologies
added 5 days ago8 views

PT-2026-50806

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 4.5.128 Description An arbitrary shell command execution issue exists where UI modules hardcode approval mode to auto, which overrides the administrator configuration set in the PRAISON APPROVAL MODE environment...

8.8CVSS6.3AI score
Exploits0References5
Rows per page
Query Builder