Cortex Agent MCP Server
cortex-agent
npm
v1.5.0
Published by kucell — no publish provenance and no vendor-owned scope, so the publisher could not be verified. The repository link below is self-declared.
Every server starts at 100. These are the exact deductions the deterministic engine applied — each one reproducible, none of it an opinion or an LLM's guess:
| Points | What was found | Category |
|---|---|---|
| −9.5 | Untrusted input concatenated into a command sink ×2 MTC-SRC-009 | injection |
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 the deduction.
Findings 12
high Shell/command execution in server code (lib/commands.js)MTC-SRC-002
In the server's implementation (`lib/commands.js:7`): 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: child_process
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 lib/commands.js
high Shell/command execution in server code (lib/git.js)MTC-SRC-002
In the server's implementation (`lib/git.js:5`): 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: child_process
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 lib/git.js
high Shell/command execution in server code (templates/en/.agent/handoffs/scripts/handoff-protocol.js)MTC-SRC-002
In the server's implementation (`templates/en/.agent/handoffs/scripts/handoff-protocol.js:6`): 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: child_process
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 templates/en/.agent/handoffs/scripts/handoff-protocol.js
high Shell/command execution in server code (templates/en/.agent/plugins/graphify/scripts/extract-subgraph.js)MTC-SRC-002
In the server's implementation (`templates/en/.agent/plugins/graphify/scripts/extract-subgraph.js:16`): 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: child_process
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 templates/en/.agent/plugins/graphify/scripts/extract-subgraph.js
high Shell/command execution in server code (templates/en/.agent/plugins/graphify/scripts/post-commit-update.cjs)MTC-SRC-002
In the server's implementation (`templates/en/.agent/plugins/graphify/scripts/post-commit-update.cjs:13`): 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: child_process
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 templates/en/.agent/plugins/graphify/scripts/post-commit-update.cjs
high Shell/command execution in server code (templates/en/.agent/plugins/graphify/scripts/post-commit-update.js)MTC-SRC-002
In the server's implementation (`templates/en/.agent/plugins/graphify/scripts/post-commit-update.js:13`): 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: child_process
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 templates/en/.agent/plugins/graphify/scripts/post-commit-update.js
high Shell/command execution in server code (templates/en/.agent/skills/agent-dashboard/scripts/generate.js)MTC-SRC-002
In the server's implementation (`templates/en/.agent/skills/agent-dashboard/scripts/generate.js:6`): 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: child_process
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 templates/en/.agent/skills/agent-dashboard/scripts/generate.js
high Shell/command execution in server code (templates/en/.agent/skills/agent-dashboard/scripts/serve.js)MTC-SRC-002
In the server's implementation (`templates/en/.agent/skills/agent-dashboard/scripts/serve.js:22`): 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: child_process
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 templates/en/.agent/skills/agent-dashboard/scripts/serve.js
high Shell/command execution in server code (templates/en/.agent/skills/management-api/scripts/index.js)MTC-SRC-002
In the server's implementation (`templates/en/.agent/skills/management-api/scripts/index.js:6`): 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: child_process
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 templates/en/.agent/skills/management-api/scripts/index.js
high Shell/command execution in server code (templates/en/.agent/skills/runtime-state-mcp/scripts/server.js)MTC-SRC-002
In the server's implementation (`templates/en/.agent/skills/runtime-state-mcp/scripts/server.js:5`): 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: child_process
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 templates/en/.agent/skills/runtime-state-mcp/scripts/server.js
medium Untrusted input concatenated into a command sink (lib/commands.js)MTC-SRC-009
In the server's implementation (`lib/commands.js:520`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: execSync(`git add -- ${
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server lib/commands.js
medium Untrusted input concatenated into a command sink (lib/git.js)MTC-SRC-009
In the server's implementation (`lib/git.js:13`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: execSync(`git ls-files --error-unmatch -- "${
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 lib/git.js
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions
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 |
|---|---|---|---|---|
v1.5.0 latest |
A 91/100 | 12 | 1.5.0 | 2026-07-22 |
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 cortex-agent --onlineMore in AI, Memory & Reasoning
Security scan results for the 402md MCP server.
Security scan results for the Acheron MCP server.
Security scan results for the Adaptive Recall MCP server.
Security scan results for the Agent Memory MCP server.
Security scan results for the Agent Memory MCP server.
Security scan results for the Agent Memory MCP server.