audit_untrusted_document — MalwareTracker Document Malware & AI Safety Scanner MCP Prompt
audit_untrusted_document
is one of 1 prompt on the
MalwareTracker Document Malware & AI Safety Scanner
MCP server. Connect the server and it appears in your client, ready to invoke.
by client
How to invoke audit_untrusted_document from your client
- Claude Code MalwareTracker Document Malware & AI Safety Scanner Prompt/audit_untrusted_document run in your project directory
- Claude Desktop MalwareTracker Document Malware & AI Safety Scanner Prompt/audit_untrusted_document ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor MalwareTracker Document Malware & AI Safety Scanner Prompt/audit_untrusted_document ~/.cursor/mcp.json
- VS Code MalwareTracker Document Malware & AI Safety Scanner Prompt/audit_untrusted_document .vscode/mcp.json
- Zed MalwareTracker Document Malware & AI Safety Scanner Prompt/audit_untrusted_document ~/.config/zed/settings.json
- Windsurf MalwareTracker Document Malware & AI Safety Scanner Prompt/audit_untrusted_document ~/.codeium/windsurf/mcp_config.json
- Cline MalwareTracker Document Malware & AI Safety Scanner Prompt/audit_untrusted_document ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI MalwareTracker Document Malware & AI Safety Scanner Prompt/audit_untrusted_document ~/.gemini/settings.json
- Grok MalwareTracker Document Malware & AI Safety Scanner Prompt/audit_untrusted_document .mcp.json (in your project root)
- ChatGPT MalwareTracker Document Malware & AI Safety Scanner Prompt/audit_untrusted_document Settings → Connectors → Advanced → Developer mode
- Claude.ai MalwareTracker Document Malware & AI Safety Scanner Prompt/audit_untrusted_document Settings → Connectors → Add custom connector
- LangChain MalwareTracker Document Malware & AI Safety Scanner Prompt/audit_untrusted_document pip install langchain-mcp-adapters
Read from the server itself, by connecting to it and calling prompts/list on 14 November 2026.
A listing does not declare its prompts, so asking is the only way to know them, and this
is what the server actually offers rather than what its listing claims. Names only are
stored; connect the server for each prompt's arguments.