24201 matches found
CVE-2026-81102
CVE-2026-81102 affects the Dropbox Dash MCP server (src/mcp_server_dash.py), which in its network mode bound its listener to the loopback address but never validated the Host header , and included no transport-security settings. This allowed a DNS rebinding attack: a malicious page in a visitor's...
CVE-2026-81102 Dropbox Dash MCP Server DNS Rebinding via Missing Host Header Validation
The Dash MCP server bound its listener to the loopback address but never checked the host a request named. src/mcpserverdash.py constructed the server for its network mode with the interface restricted to loopback and no transport-security settings, so a name that had been pointed at the loopback...
CVE-2026-81093
The get-html-skeleton tool fetched a URL the caller supplied after checking only its syntax. The handler in src/tools/common/gethtmlskeleton.ts validated the url argument with isValidHttpUrl from src/utils/generic.ts, which confirmed the string began with an http or https scheme and parsed as a U...
Malicious Package
Overview yamlformat-tools is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this package...
CVE-2026-1492-POC
Questo repository non contiene un README...
CVE-2026-37007
A vulnerability in FileWriterTool in crewai-tools = 1.10.2rc1 allows a remote attacker to achieve code execution via malicious path traversal sequences in the filename argument...
CVE-2026-37007: Improper Limitation of a Pathname to a Restricted Directory
A vulnerability in FileWriterTool in crewai-tools = 1.10.2rc1 allows a remote attacker to achieve code execution via malicious path traversal sequences in the filename argument...
EUVD-2026-67269
A vulnerability in FileWriterTool in crewai-tools = 1.10.2rc1 allows a remote attacker to achieve code execution via malicious path traversal sequences in the filename argument...
PT-2026-82664
Name of the Vulnerable Software and Affected Versions crewai-tools versions prior to 1.10.3 Description A flaw in the FileWriterTool allows a remote attacker to execute arbitrary code. This is achieved by using malicious path traversal sequences—a technique used to access files and directories...
CVE-2026-37007
A vulnerability exists in the FileWriterTool component of crewai-tools (versions
CVE-2026-37007
A vulnerability in FileWriterTool in crewai-tools = 1.10.2rc1 allows a remote attacker to achieve code execution via malicious path traversal sequences in the filename argument...
CVE-2026-81093: Server-Side Request Forgery (SSRF)
The get-html-skeleton tool fetched a URL the caller supplied after checking only its syntax. The handler in src/tools/common/gethtmlskeleton.ts validated the url argument with isValidHttpUrl from src/utils/generic.ts, which confirmed the string began with an http or https scheme and parsed as a U...
EUVD-2026-67268
A SQL injection vulnerability in NL2SQLTool in crewai-tools v1.10.2rc1 allows a remote attacker to execute arbitrary SQL commands via an unsanitized sqlquery argument...
PT-2026-82665
Name of the Vulnerable Software and Affected Versions crewai-tools version 1.10.2rc1 Description A SQL injection issue exists in the NL2SQLTool component. A remote attacker can execute arbitrary SQL commands by providing an unsanitized sql query argument. SQL injection is a technique where...
CVE-2026-37009
The crewai-tools library, specifically version v1.10.2rc1 , contains a SQL injection vulnerability within the NL2SQLTool component. This flaw allows a remote attacker to execute arbitrary SQL commands because the sql_query argument is improperly neutralized and processed without sufficient saniti...
CVE-2026-37009
A SQL injection vulnerability in NL2SQLTool in crewai-tools v1.10.2rc1 allows a remote attacker to execute arbitrary SQL commands via an unsanitized sqlquery argument...
CVE-2026-37009
A SQL injection vulnerability in NL2SQLTool in crewai-tools v1.10.2rc1 allows a remote attacker to execute arbitrary SQL commands via an unsanitized sqlquery argument...
ContextLeak: Exfiltrating LLM Agent Context Via Malicious Tools
Exfiltrating an LLM agent's runtime context -- such as the user prompt, execution trajectory, and tool list -- poses severe security and privacy risks to users. Such attacks can be carried out via malicious tools and typically require three conditions: 1 the agent selects the malicious tool for...