Qwen Core MCP Server
qwen-core
npm
v2.3.0
Published by youssefvdel — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 11 = 89. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −10 | capability blast radius (critical) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 33
critical Completed toxic-flow trifecta across toolsMTC-FLOW-002
This server (without client built-ins) exposes a complete data-exfiltration chain: web_fetch → bash → execute_command. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.
Fix: Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.
Location: flow web_fetch → bash → execute_command
high Read-and-egress in one tool: "bash"MTC-FLOW-003
Tool "bash" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.
Fix: Separate reading from sending; require explicit user confirmation before egress of file/secret contents.
Location: flow bash
high Read-and-egress in one tool: "execute_command"MTC-FLOW-003
Tool "execute_command" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.
Fix: Separate reading from sending; require explicit user confirmation before egress of file/secret contents.
Location: flow execute_command
high Tool "bash" exposes command/code executionMTC-CAP-001
Tool "bash" appears to run shell commands or evaluate code (keyword "bash" in tool name, parameter "command"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool bash
high Tool "execute_command" exposes command/code executionMTC-CAP-001
Tool "execute_command" appears to run shell commands or evaluate code (keyword "execute command" in tool name, parameter "command"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool execute_command
high Shell/command execution in server code (dist/agent/AutonomousAgent.js)MTC-SRC-002
In the server's implementation (`dist/agent/AutonomousAgent.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { exec } from 'child_process'; import { promisify } from 'util'; const execAsync = promisify(exec); export clas
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/agent/AutonomousAgent.js
high Shell/command execution in server code (dist/index.mjs)MTC-SRC-002
In the server's implementation (`dist/index.mjs:155`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ; import { exec } from "child_process"; import { promisify } from "util"; function getAutonomousAgent(config) { if (!a
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/index.mjs
high Shell/command execution in server code (dist/tools/BashTool.js)MTC-SRC-002
In the server's implementation (`dist/tools/BashTool.js:2`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ; import { exec } from 'child_process'; import { promisify } from 'util'; import { BaseTool } from './BaseTool.js'; cons
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/BashTool.js
high Shell/command execution in server code (dist/tools/GrepTool.js)MTC-SRC-002
In the server's implementation (`dist/tools/GrepTool.js:2`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ; import { exec } from 'child_process'; import { promisify } from 'util'; import * as path from 'path'; import { BaseToo
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/GrepTool.js
medium Hardcoded egress to an external endpoint (dist/index.js)MTC-SRC-003
In the server's implementation (`dist/index.js:1768`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch(`https://duckduckgo.com/html?q=${query}&kl=wt-wt`, { headers: { "User-
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/index.js
medium Unconstrained URL/host parameter "url" on "web_fetch"MTC-CAP-007
Tool "web_fetch" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool web_fetch · inputSchema.properties.url
medium Tool "write_file" can modify the filesystemMTC-CAP-002
Tool "write_file" can write, overwrite or delete files (keyword "write_file" in tool name). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool write_file
medium Tool "edit_file" can modify the filesystemMTC-CAP-002
Tool "edit_file" can write, overwrite or delete files (keyword "edit_file" in tool name). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool edit_file
medium Tool "move_file" can modify the filesystemMTC-CAP-002
Tool "move_file" can write, overwrite or delete files (keyword "move_file" in tool name). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool move_file
medium Tool "delete_file" can modify the filesystemMTC-CAP-002
Tool "delete_file" can write, overwrite or delete files (keyword "delete_file" in tool name). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool delete_file
medium Unconstrained command parameter "command" on "bash"MTC-CAP-006
Tool "bash" takes a command-shaped parameter "command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool bash · inputSchema.properties.command
medium Unconstrained command parameter "command" on "execute_command"MTC-CAP-006
Tool "execute_command" takes a command-shaped parameter "command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool execute_command · inputSchema.properties.command
low Mutating tool "bash" declares no destructiveHintMTC-CAP-005
Tool "bash" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool bash
low Mutating tool "write_file" declares no destructiveHintMTC-CAP-005
Tool "write_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool write_file
low Mutating tool "edit_file" declares no destructiveHintMTC-CAP-005
Tool "edit_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool edit_file
low Mutating tool "move_file" declares no destructiveHintMTC-CAP-005
Tool "move_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool move_file
low Mutating tool "delete_file" declares no destructiveHintMTC-CAP-005
Tool "delete_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool delete_file
low Mutating tool "execute_command" declares no destructiveHintMTC-CAP-005
Tool "execute_command" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool execute_command
low Unconstrained path parameter "path" on "read_file"MTC-CAP-008
Tool "read_file" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool read_file · inputSchema.properties.path
low Unconstrained path parameter "path" on "write_file"MTC-CAP-008
Tool "write_file" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool write_file · inputSchema.properties.path
low Unconstrained path parameter "path" on "edit_file"MTC-CAP-008
Tool "edit_file" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool edit_file · inputSchema.properties.path
low Unconstrained path parameter "path" on "grep_search"MTC-CAP-008
Tool "grep_search" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool grep_search · inputSchema.properties.path
low Unconstrained path parameter "path" on "read_text_file"MTC-CAP-008
Tool "read_text_file" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool read_text_file · inputSchema.properties.path
low Unconstrained path parameter "path" on "list_directory"MTC-CAP-008
Tool "list_directory" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool list_directory · inputSchema.properties.path
low Unconstrained path parameter "path" on "directory_tree"MTC-CAP-008
Tool "directory_tree" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool directory_tree · inputSchema.properties.path
low Unconstrained path parameter "path" on "search_files"MTC-CAP-008
Tool "search_files" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool search_files · inputSchema.properties.path
low Unconstrained path parameter "path" on "get_file_info"MTC-CAP-008
Tool "get_file_info" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool get_file_info · inputSchema.properties.path
low Unconstrained path parameter "path" on "delete_file"MTC-CAP-008
Tool "delete_file" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool delete_file · inputSchema.properties.path
Tools 53
Each tool and what it can reach — statically extracted from the published source.
bashreads sensitive dataruns code / shelledit_filereads sensitive datawrites filesexecute_commandreads sensitive dataruns code / shellwrite_filereads sensitive datawrites filesdelete_filewrites filesdirectory_treereads sensitive dataget_file_inforeads sensitive dataglob_searchreads sensitive datagrep_searchreads sensitive datalist_directoryreads sensitive data
Show 43 more tools ↓
load_categoryreads sensitive datamove_filewrites filesread_filereads sensitive dataread_multiple_filesreads sensitive dataread_text_filereads sensitive datasearch_filesreads sensitive datasequential_thinkingreads sensitive dataweb_fetchingests untrusted inputweb_searchingests untrusted inputask_userno sensitive capabilityautonomous_agentno sensitive capabilityautonomous-agentno sensitive capabilitycategory-gatewayno sensitive capabilityclear_error_memoryno sensitive capabilitycommandno sensitive capabilitycontextno sensitive capabilityconvert_timeno sensitive capabilitycreate_directoryno sensitive capabilitydelete_directoryno sensitive capabilityerror_memory_statusno sensitive capabilityfrontend-designno sensitive capabilityget_current_timeno sensitive capabilitygit_addno sensitive capabilitygit_commitno sensitive capabilitygit_diffno sensitive capabilitygit_logno sensitive capabilitygit_statusno sensitive capabilityintentno sensitive capabilitykill_processno sensitive capabilitylist_categoriesno sensitive capabilitylist_directory_with_sizesno sensitive capabilitylist_processesno sensitive capabilitylist_skillsno sensitive capabilityqwen-coreno sensitive capabilityread_pdfno sensitive capabilityskill-auto-loaderno sensitive capabilityskill-loaderno sensitive capabilityskillNameno sensitive capabilityslash-commandno sensitive capabilitytaskno sensitive capabilitytask-plannerno sensitive capabilitythink-firstno sensitive capabilitytodo_writeno sensitive capability
Toxic flows 3
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (53 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v2.3.0 latest |
B 89/100 | 33 | 1.9.0 | 2026-07-24 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan qwen-core --onlineMore in Developer Tools
Security scan results for the 1stay MCP server.
Security scan results for the Adguard Home MCP server.
Security scan results for the Ado Browser MCP server.
Security scan results for the Adobe Experience Dev MCP server.
Security scan results for the Aemet MCP server.
Security scan results for the Affinity Mcp Bridge MCP server.