Lucene search
+L

1604 matches found

EUVD
EUVD
•added 2026/08/24 5:55 p.m.•13 views

EUVD-2026-65059

The Continue CLI applies an incomplete denylist as its only barrier to destructive shell commands when running unattended. In headless mode and auto mode the default policy in extensions/cli/src/permissions/defaultPolicies.ts grants the Bash tool the allow permission, and permissionChecker.ts...

8.3CVSS5.5AI score0.00392EPSS
SaveExploits0References5
CVE
CVE
•added 2026/08/24 5:55 p.m.•32 views

CVE-2026-76072

Continue CLI through 1.5.47 uses an incomplete denylist in evaluateTerminalCommandSecurity.ts as its sole barrier against destructive shell commands in headless and auto modes. The dangerous-path check covers only /, ~, /usr, /etc, /bin, and /sbin, leaving paths like /home, /root, /var, /opt, and...

8.3CVSS5.9AI score0.00392EPSS
SaveExploits0References5
Vulnrichment
Vulnrichment
•added 2026/08/24 5:55 p.m.•12 views

CVE-2026-76072 Continue CLI through 1.5.47 Incomplete Destructive Command Denylist in Headless and Auto Mode

The Continue CLI applies an incomplete denylist as its only barrier to destructive shell commands when running unattended. In headless mode and auto mode the default policy in extensions/cli/src/permissions/defaultPolicies.ts grants the Bash tool the allow permission, and permissionChecker.ts...

8.3CVSS5.9AI score0.00392EPSS
SaveExploits0References5
Cvelist
Cvelist
•added 2026/08/24 5:55 p.m.•36 views

CVE-2026-76072 Continue CLI through 1.5.47 Incomplete Destructive Command Denylist in Headless and Auto Mode

The Continue CLI applies an incomplete denylist as its only barrier to destructive shell commands when running unattended. In headless mode and auto mode the default policy in extensions/cli/src/permissions/defaultPolicies.ts grants the Bash tool the allow permission, and permissionChecker.ts...

8.3CVSS0.00392EPSS
SaveExploits0References5
GithubExploit
GithubExploit
•added 2026/08/24 8:29 a.m.•34 views

leash-poc

leash-poc: MCP tool-poisoning, contained by an independent pol...

8.8CVSS7.5AI score0.24429EPSS
SaveExploits7
Kitploit
Kitploit
•added 2026/08/24 12:18 a.m.•10 views

hermetic

Der agentenisolierte Credential-Broker. Ihr KI-Agent führt den authentifizierten Aufruf durch. Er sieht nie den Schlüssel. -brightgreen?style=flat-square Webseite · Installation · Schnellstart · Funktionsweise · Sicherheitsmodell · Schwachstelle melden !IMPORTANT Ihr KI-Agent arbeitet auf der ★★★...

5.6AI score
SaveExploits0References11
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/08/24 12:00 a.m.•2 views

CVE-2026-76072: Incomplete List of Disallowed Inputs

The Continue CLI applies an incomplete denylist as its only barrier to destructive shell commands when running unattended. In headless mode and auto mode the default policy in extensions/cli/src/permissions/defaultPolicies.ts grants the Bash tool the allow permission, and permissionChecker.ts...

8.3CVSS5.8AI score0.00392EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/08/24 12:00 a.m.•25 views

PT-2026-80986

The Continue CLI applies an incomplete denylist as its only barrier to destructive shell commands when running unattended. In headless mode and auto mode the default policy in extensions/cli/src/permissions/defaultPolicies.ts grants the Bash tool the allow permission, and permissionChecker.ts...

7.4CVSS5.4AI score0.00392EPSS
SaveExploits0References6
Vulnrichment
Vulnrichment
•added 2026/08/21 12:07 p.m.•15 views

CVE-2026-59318 DefaultToolCallingManager Global Resolver Fallback Allows Unadvertised Tool Dispatch via Prompt Injection

In Spring AI's tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege...

6.5CVSS5.8AI score0.00254EPSS
SaveExploits0References1
Cvelist
Cvelist
•added 2026/08/21 12:07 p.m.•45 views

CVE-2026-59318 DefaultToolCallingManager Global Resolver Fallback Allows Unadvertised Tool Dispatch via Prompt Injection

In Spring AI's tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege...

6.5CVSS0.00254EPSS
SaveExploits0References1
CVE
CVE
•added 2026/08/21 12:07 p.m.•72 views

CVE-2026-59318

CVE-2026-59318 is an Incorrect Authorization flaw in Spring AI 's tool calling support, specifically in DefaultToolCallingManager within the org.springframework.ai:spring-ai-model package. The per-request tool list is advertised to the model as a boundary but is not fully enforced at dispatch tim...

9.8CVSS5.8AI score0.00254EPSS
SaveExploits0References1Affected Software1
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/08/21 12:00 a.m.•2 views

CVE-2026-62676: Incomplete List of Disallowed Inputs

Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, the shared shell-command parser in omnigent/policies/builtins/shell.py fails to recognize combined interpreter flags, the timeout, nice, setsid, and stdbuf wrappers, command...

7.1CVSS5.9AI score0.00402EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/08/21 12:00 a.m.•41 views

PT-2026-79457

Name of the Vulnerable Software and Affected Versions Xinference versions prior to 2.7.0 Description Xinference passes attacker-influenced Llama3 tool-call output to the eval function within xinference/model/llm/tool parsers/llama3 tool parser.py and xinference/model/llm/utils.py. Requests sent t...

10CVSS6.2AI score0.01226EPSS
SaveExploits0References15
Kitploit
Kitploit
•added 2026/08/20 9:51 a.m.•17 views

SecureAI-Scan v0.10.0

SecureAI-Scan The AI security scanner that proves its findings. SecureAI-Scan finds LLM, MCP, Agent Skill, and RAG vulnerabilities in TypeScript, JavaScript, and Python — and shows you the evidence: the exact source → flow → sink path for every dataflow finding, resolved through real imports, not...

9.6CVSS8.7AI score0.77657EPSS
SaveExploits1References36
EUVD
EUVD
•added 2026/08/20 12:35 a.m.•20 views

EUVD-2026-63135

Agno's PythonTools in libs/agno/agno/tools/python.py contains a path traversal vulnerability that allows attackers to read, write, or execute arbitrary files by supplying parent-directory traversal sequences in the filename argument passed to readfile, savetofile, or runpythonfile tool actions...

8.8CVSS6.3AI score0.01256EPSS
SaveExploits0References4
OSV
OSV
•added 2026/08/19 9:58 p.m.•20 views

CVE-2026-76832 Agno PythonTools Path Traversal via joinpath file_name argument

Agno's PythonTools in libs/agno/agno/tools/python.py contains a path traversal vulnerability that allows attackers to read, write, or execute arbitrary files by supplying parent-directory traversal sequences in the filename argument passed to readfile, savetofile, or runpythonfile tool actions...

8.5CVSS6.5AI score
SaveExploits0References5
Circl
Circl
•added 2026/08/19 8:35 p.m.•39 views

CVE-2026-54689

creationtimestamp| type| source ---|---|--- 2026-08-19 20:35:08+00:00| published-proof-of-concept| https://github.com/ihor-sokoliuk/mcp-searxng/security/advisories/GHSA-wppf-h75h-6pm6...

6.3CVSS5.8AI score0.0019EPSS
SaveExploits0References1
OSV
OSV
•added 2026/08/19 7:15 p.m.•11 views

GHSA-RR55-JP92-8WP2 claude-faf-mcp has an arbitrary local file read/write via unconfined `path` argument in FAF tools

Summary claude-faf-mcp MCP tools accept a caller-controlled path argument and resolve it expansion + path.resolve straight into a filesystem read/write without confining it to a trusted project directory. An absolute path or ../ traversal is resolved and used as-is, so the server process can be...

7.5CVSS5.4AI score
SaveExploits0References3
Github Security Blog
Github Security Blog
•added 2026/08/19 7:15 p.m.•22 views

faf-mcp has an arbitrary local file read/write via unconfined `path` argument in FAF tools

Summary faf-mcp MCP tools accept a caller-controlled path argument and resolve it expansion + path.resolve straight into a filesystem read/write without confining it to a trusted project directory. An absolute path or ../ traversal is resolved and used as-is, so the server process can be made to...

5.3AI score
SaveExploits0References3Affected Software1
OSV
OSV
•added 2026/08/19 7:15 p.m.•11 views

GHSA-CC2G-GQ8C-R332 grok-faf-mcp has an arbitrary local file read via unconfined `path` argument in FAF tools

Summary Several grok-faf-mcp MCP tools accept a caller-controlled path argument and resolve it expansion + path.resolve straight into a filesystem read without confining it to a trusted project directory. An absolute path or ../ traversal is resolved and used as-is, so the server process can be...

7.5CVSS5.4AI score
SaveExploits0References3
Rows per page
Query Builder