Lucene search
+L

12 matches found

NVD
NVD
•added 2026/09/14 4:17 p.m.•14 views

CVE-2026-57145

PraisonAI is a multi-agent teams system. Prior to 4.6.62, src/praisonai/praisonai/tools/multiedit.py passes the LLM-controlled filepath parameter directly to open for reading and writing without traversal rejection, symlink resolution, a workspace boundary, or protected-path checks...

9.1CVSS0.00544EPSS
SaveExploits0References3
NVD
NVD
•added 2026/09/14 3:17 p.m.•14 views

CVE-2026-57130

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, src/praisonai-agents/praisonaiagents/tools/emailtools.py interpolates LLM-controlled fromaddr, subject, and query values directly into quoted IMAP SEARCH criteria. Embedded quote, backslash, newline, or null characters can...

8.1CVSS0.00462EPSS
SaveExploits0References3
CVE
CVE
•added 2026/09/14 3:10 p.m.•23 views

CVE-2026-57145

CVE-2026-57145 affects PraisonAI , an AI multi-agent framework. The multiedit tool in src/praisonai/praisonai/tools/multiedit.py passes the LLM-controlled filepath parameter directly to open() for reading and writing without path traversal rejection, symlink resolution, workspace boundary validat...

9.1CVSS5.9AI score0.00544EPSS
SaveExploits0References3
OSV
OSV
•added 2026/09/14 2:28 p.m.•18 views

CVE-2026-57130 PraisonAI: IMAP Command Injection via Unsanitized Email Search Parameters

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, src/praisonai-agents/praisonaiagents/tools/emailtools.py interpolates LLM-controlled fromaddr, subject, and query values directly into quoted IMAP SEARCH criteria. Embedded quote, backslash, newline, or null characters can...

8.1CVSS5.7AI score
SaveExploits0References5
EUVD
EUVD
•added 2026/09/14 2:28 p.m.•10 views

EUVD-2026-77534

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, src/praisonai-agents/praisonaiagents/tools/emailtools.py interpolates LLM-controlled fromaddr, subject, and query values directly into quoted IMAP SEARCH criteria. Embedded quote, backslash, newline, or null characters can...

8.1CVSS5.7AI score0.00462EPSS
SaveExploits0References3
CVE
CVE
•added 2026/09/14 2:28 p.m.•30 views

CVE-2026-57130

PraisonAI (praisonaiagents) is a multi-agent framework. Prior to 1.6.59 , the file email_tools.py interpolates LLM-controlled parameters (from_addr, subject, query, search_id) directly into IMAP SEARCH criteria using f-string formatting with double-quote delimiters, with no escaping or sanitizati...

8.1CVSS5.9AI score0.00462EPSS
SaveExploits0References3
PyPA
PyPA
•added 2026/09/10 9:44 a.m.•18 views

praisonaiagents: ast_grep_rewrite rewrites arbitrary files without the @require_approval gate enforced on every sibling mutation tool

Target: PraisonAI MervinPraison/PraisonAIAffected component: praisonaiagents/tools/astgreptool.py — astgreprewriteAffected versions: master at ce97667156a116c50b4a3d1aa21e09f048903fda; reproduced against the current praisonaiagents PyPI release praisonaiagents = 1.6.52. SummaryTools in...

6.1CVSS6.3AI score0.00166EPSS
SaveExploits0References7Affected Software1
Github Security Blog
Github Security Blog
•added 2026/09/04 6:02 p.m.•14 views

CodeWhale: exec_shell_interact sends LLM-controlled input to a running shell without an approval prompt (privilege escalation)

Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 57f3c89471e27ac4032d9791f6885e5d4408c381. Users should upgrade to 0.8.64 or later. The original reporter analysis is...

7.3CVSS6.2AI score0.00155EPSS
SaveExploits0References5Affected Software3
OSV
OSV
•added 2026/09/04 6:02 p.m.•13 views

GHSA-G29H-PFMP-QP9R CodeWhale: exec_shell_interact sends LLM-controlled input to a running shell without an approval prompt (privilege escalation)

Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 57f3c89471e27ac4032d9791f6885e5d4408c381. Users should upgrade to 0.8.64 or later. The original reporter analysis is...

7.3CVSS6.1AI score0.00155EPSS
SaveExploits0References5
OSV
OSV
•added 2026/08/25 2:46 p.m.•10 views

GHSA-CFXV-8FW8-RWPV praisonaiagents: ast_grep_rewrite rewrites arbitrary files without the @require_approval gate enforced on every sibling mutation tool

Target: PraisonAI MervinPraison/PraisonAI Affected component: praisonaiagents/tools/astgreptool.py — astgreprewrite Affected versions: master at ce97667156a116c50b4a3d1aa21e09f048903fda; reproduced against the current praisonaiagents PyPI release praisonaiagents --rewrite --lang --update-all line...

6.1CVSS6.3AI score0.00166EPSS
SaveExploits0References4
Github Security Blog
Github Security Blog
•added 2026/08/19 7:17 p.m.•17 views

Contentful MCP Server: export_space/import_space tools pass LLM-controlled `host`/`proxy` args to CMA client, redirecting server PAT to attacker-controlled endpoint

Summary exportspace and importspace tools in @contentful/mcp-tools accept LLM-controlled host and proxy parameters that are spread directly into the options object passed to contentful-export / contentful-import. These libraries pass the merged options — including the attacker-controlled host — t...

7.7CVSS6.1AI score0.00415EPSS
SaveExploits0References6Affected Software2
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/08/18 12:00 a.m.•3 views

CVE-2026-75857: Improper Privilege Management

CodeWhale versions = 0.8.41 and 0.8.64 contain a vulnerability in the execshellinteract alias execinteract tool, whose approvalrequirement returns ApprovalRequirement::Auto. This overrides the default Required approval for code-executing tools, so LLM-controlled stdin is written into an...

7.3CVSS5.8AI score0.00155EPSS
SaveExploits0References2
Rows per page
Query Builder