@mseep/pgpt-mcp-server
Score-based assessment (critical risk, 100/100). An AI review is available in the AI review tab.
Analysis record
- Analysed
- 2 weeks ago 5 November 2026
- Version
- v2.1.0
- Artifact
- SHA256 44fa5438…0655b8
- Detail
- Partial list
Evidence ledger
Ranked by severity · findings with a source location link to the code viewer
YARA Rule Matches
18 rules| Severity | Rule | Hits | Files | Metadata |
|---|---|---|---|---|
| LOW | credential ssh keys | 5 | pgpt.env.json.exampleREADME.mdver/index_proxy_np.js +2 more | - |
| LOW | LocalStorageShouldNotBeUsed | 1 | clients/Gradio/main.py | - |
| LOW | spyeye | 17 | clients/C++/5.1 mcp_edit_user/MCPEditUserClient.execlients/C++/2.0 mcp_chat/MCPChatClient.execlients/C++/3.0 mcp_create_source/MCPCreateSourceClient.exe +14 more | - |
| LOW | PM Zip with js | 16 | clients/C# .Net/2.0 mcp_chat/obj/Debug/net9.0/mcp_chat.assets.cacheclients/C# .Net/3.3 mcp_edit_source/obj/Debug/net9.0/mcp_edit_source.assets.cacheclients/C# .Net/5.2 mcp_delete_user/obj/Debug/net9.0/mcp_delete_user.assets.cache +13 more | - |
| LOW | postinstall persistence mechanism | 23 | clients/C++/5.0 mcp_store_user/MCPStoreUserClient.cppclients/Gradio/mcp_client.pyagents/MCP-Client/Python/environment.py +20 more | - |
| LOW | credential env files | 19 | agents/MCP-Client/Python/mcp_client_sse.pyclients/Gradio/mcp_client.pyagents/MCP-Client/Python/config.py +16 more | - |
| LOW | NoDisableTlsRejectUnauthorized | 2 | clients/Gradio/mcp_servers/demo-mcp-server/tools/weather.jsclients/Gradio/mcp_servers/demo-mcp-server/tools/assets.js | - |
| LOW | postinstall file download | 86 | clients/C# .Net/2.0 mcp_chat/bin/Debug/net9.0/mcp_chat.pdbagents/IoTAgent/Python/iot_mqtt_agent.pyclients/C# .Net/5.1 mcp_edit_user/bin/Debug/net9.0/mcp_edit_user.pdb +83 more | - |
| LOW | SQLInjection | 2 | src/pgpt-messages.jsdist/pgpt-messages.js | - |
| LOW | postinstall crypto operations | 4 | ver/index_np.jsclients/C# .Net/4.0 mcp_list_groups/bin/Debug/net9.0/mcp_list_groups.deps.jsonclients/C# .Net/5.2 mcp_delete_user/bin/Debug/net9.0/mcp_delete_user.pdb +1 more | - |
| LOW | postinstall system command | 222 | clients/C# .Net/1.0 mcp_login/bin/Debug/net9.0/mcp_login.pdbclients/C# .Net/5.1 mcp_edit_user/bin/Debug/net9.0/mcp_edit_user.pdbclients/PHP/2.1 mcp_continue_chat/MCPContinueChatClient.php +219 more | - |
| LOW | UsingShellInterpreterWhenExecutingOSCommands | 1 | clients/Gradio/mcp_servers/arxiv/arxiv-stdio.js | - |
| LOW | postinstall network communication | 241 | clients/C++/4.1 mcp_store_group/MCPStoreGroupClient.cppclients/C# .Net/Code Archiv/mcp_list_sources.csclients/Go/3.3 mcp_edit_source/MCPEditSourceClient.go +238 more | - |
| LOW | postinstall obfuscation | 78 | clients/Gradio/config.pyclients/PHP/2.1 mcp_continue_chat/MCPContinueChatClient.phpclients/Python/4.0 mcp_list_groups/MCPListGroupsClient.py +75 more | - |
| LOW | postinstall registry modification | 32 | clients/C# .Net/5.2 mcp_delete_user/obj/Debug/net9.0/mcp_delete_user.pdbclients/C# .Net/1.0 mcp_login/obj/Debug/net9.0/mcp_login.pdbclients/C# .Net/5.0 mcp_store_user/obj/Debug/net9.0/mcp_store_user.pdb +29 more | - |
| LOW | NoUseSocketManually | 16 | clients/JavaScript/4.1 mcp_store_group/MCPStoreGroupClient.jsclients/JavaScript/3.0 mcp_create_source/MCPCreateSourceClient.jsclients/JavaScript/2.1 mcp_continue_chat/MCPContinueChatClient.js +13 more | - |
| LOW | postinstall environment access | 23 | clients/Gradio/mcp_servers/demo-mcp-server/tools/weather.jsclients/Gradio/file_tools/loader_factory.pysrc/services/pgpt-service.ts +20 more | - |
| LOW | postinstall file manipulation | 92 | clients/C# .Net/4.2 mcp_delete_group/obj/project.nuget.cacheclients/PHP/2.1 mcp_continue_chat/MCPContinueChatClient.phpclients/C# .Net/3.4 mcp_delete_source/obj/Debug/net9.0/mcp_delete_source.GeneratedMSBuildEditorConfig.editorconfig +89 more | - |
Finding Categories
YARA Rules Matched
18 rules(880 hits)MCP Server Analysis
MCP servers expose tools and resources to AI assistants. Unlike browser extensions, they run as standalone processes with direct system access. Tool definitions are analyzed for prompt injection, data exfiltration, and tool poisoning patterns.
AI Security Report
AI Security Review
Evidence context: threat category none; evidence quality weak.
The supplied findings do not establish what behavior triggered the matches. A fresh analysis with the relevant code and surrounding context is needed. These findings neither establish malicious behavior nor demonstrate that the extension is safe.
Key Reasons
- Insufficient implementation context for the supplied findings
Reviewed 2026-11-14 · version 2.1.0; recommended action: reanalyze; model confidence 95%.
Source Code Not Available
Source code is not available for this version of the extension.
About This Extension
Frequently Asked Questions
Similar Extensions
Related extensions from the same publisher or marketplace