27 matches found
CVE-2026-18974
A vulnerability was found in heshengtao super-agent-party up to 0.4.1. This affects the function getfilecontent of the file server.py of the component executetoolmanually Endpoint. The manipulation of the argument toolname/toolparams results in information disclosure. The attack can be launched...
EUVD-2026-53695
A vulnerability was found in heshengtao super-agent-party up to 0.4.1. This affects the function getfilecontent of the file server.py of the component executetoolmanually Endpoint. The manipulation of the argument toolname/toolparams results in information disclosure. The attack can be launched...
CVE-2026-60087
PRAISONAI v1.6.78 and earlier are affected: PraisonAI caches tool approvals by tool name, enabling reuse of initial approvals for subsequent calls with arbitrary arguments. This can allow an attacker to obtain approval for a benign operation and then execute dangerous file write operations within...
PT-2026-59578
Summary The approval system in PraisonAI Agents caches tool approval decisions by tool name only, not by invocation arguments. Once a user approves execute command for any command e.g., ls -la, all subsequent execute command calls in that execution context bypass the approval prompt entirely...
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...
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...
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...
PT-2026-40787
Three CVEs CVE-2026-29774, CVE-2026-30015, CVE-2026-30221 exploited the fact that the protocol did not, in version 1.2, canonicalize tool names. Multiple servers in the same session could expose tools named, respectively: readfile the legitimate filesystem server…...
PT-2026-40788
Three CVEs CVE-2026-29774, CVE-2026-30015, CVE-2026-30221 exploited the fact that the protocol did not, in version 1.2, canonicalize tool names. Multiple servers in the same session could expose tools named, respectively: readfile the legitimate filesystem server…...
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,...
CVE-2026-44339 PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute
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,...
PraisonAI 安全漏洞
PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 4.6.37 and PraisonAIagents prior to 1.6.37 have security vulnerabilities. These vulnerabilities stem from unresolved tool name resolution issues, which may allow attackers to...
PT-2026-50805
Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 1.5.128 Description The software caches tool approval decisions based solely on the tool name rather than the invocation arguments. This allows subsequent calls to the execute command function to bypass approval...
SUSE CVE-2026-30856
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming...
CVE-2026-30856
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming...
CVE-2026-30856
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming...
CVE-2026-30856
WeKnora CVE-2026-30856: Pre-0.3.0 versions are vulnerable to a tool-name collision and indirect prompt injection via an MCP client naming convention (mcp_{service}_{tool}), allowing a remote MCP server to hijack tool execution and potentially exfiltrate prompts/context or run other tools with use...
CVE-2026-30856
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming...
WeKnora 安全漏洞
WeKnora is an open-source framework based on LLM developed by Tencent. It features deep document understanding using the RAG paradigm, semantic retrieval, and context-aware answers. Prior to version 0.3.0, WeKnora had security vulnerabilities. These vulnerabilities were caused by tool name...
Use of Incorrectly-Resolved Name or Reference
Overview Affected versions of this package are vulnerable to Use of Incorrectly-Resolved Name or Reference via the MCPTool.Name sanitization in the NewMCPTool registration process in internal/agent/tools. An attacker can execute arbitrary MCP tools and inject prompts to exfiltrate context by...