Is llm-router safe to use?

llm-router scores 15/100 (grade F) on the Canopii Trust Index, and carries 1 confirmed security failure that caps its score: No command-injection sinks. It passes 12 of the 20 controls that apply to it.

What security issues does llm-router have?

llm-router fails 1 control: No command-injection sinks. Each failure on this page carries the evidence behind it — the file and line, dependency, or CVE that decided it.

How reliable is the security score for llm-router?

We could evaluate 89% of the controls that apply to llm-router. Scores are deterministic — the same source always produces the same score — and a partially-scannable server cannot present a high one, because confidence caps the result. The scanner is open source, so this score can be reproduced independently.

How was llm-router scored?

Its published source was scanned against a fixed catalog of weighted security controls covering code safety, committed secrets, dependency vulnerabilities, tool-description integrity, authentication and transport, and maintenance. A confirmed flaw caps the score outright regardless of what else passes. The full rubric is published.

llm-router MCP Server Security Report

ypollak2/llm-router

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain keeps costs 70–85% lower.

15F

Security Trust Score

Grade F · Serious issues

Tier 1 · Public sourceHigh confidence · 89%latest vmain@72dd582 Repository

Declared MCP capabilities

Prompts

Run it securely

This server scored F. Run it behind runtime policy enforcement so one bad tool call can't become an incident.

Are you the maintainer?

Verify with GitHub to get alerted whenever ypollak2/llm-router changes score — and claim the badge for your README.

Claim this server

1 issue capping this score

criticalNo command-injection sinks — 1 occurrence

The short answer

Is llm-router safe to use?: llm-router scores 15/100 (grade F) on the Canopii Trust Index, and carries 1 confirmed security failure that caps its score: No command-injection sinks. It passes 12 of the 20 controls that apply to it.
What security issues does llm-router have?: llm-router fails 1 control: No command-injection sinks. Each failure on this page carries the evidence behind it — the file and line, dependency, or CVE that decided it.
How reliable is the security score for llm-router?: We could evaluate 89% of the controls that apply to llm-router. Scores are deterministic — the same source always produces the same score — and a partially-scannable server cannot present a high one, because confidence caps the result. The scanner is open source, so this score can be reproduced independently.
How was llm-router scored?: Its published source was scanned against a fixed catalog of weighted security controls covering code safety, committed secrets, dependency vulnerabilities, tool-description integrity, authentication and transport, and maintenance. A confirmed flaw caps the score outright regardless of what else passes. The full rubric is published.

Reputation63stars9forks0open issues3d agolast commit<1yage

Security controlslatest scored version vmain@72dd582

Each control is evaluated deterministically with evidence. The score is earned from passing controls; a failed guard caps it.

Model–MCP Runtime Guardrails

Pass
Indirect Prompt Injection (IPI) Defensesguardno injection markers
Tool/prompt/resource text is free of hidden instructions that could hijack the agent.
Pass
Strict JSON Schema EnforcementadditionalProperties:false present
Tool inputs are constrained (additionalProperties:false), so unexpected arguments can't be smuggled in.
Pass
User-in-the-Loop / Approval Scopeguardno destructive tool scope
No over-broad or destructive tools (arbitrary shell, bulk-delete) that warrant human approval.
N/A
Tool Definition Integrityguardno prior version to diff
Every consecutive version pair is diffed for new injection markers or destructive scope — a risky diff anywhere in history is a rug-pull (fail, durable); benign description drift warns.

Application Security Checks

Fail
No command-injection sinksguard1 occurrence
Untrusted tool input reaching a shell yields remote code execution. How many servers fail this?
src/llm_router/hooks/agent_loop.py:232
Fix: Never pass tool arguments to a shell; use argv arrays with shell disabled.
Warn
No path traversalguard5 occurrences
Naive path checks let tools read/write outside intended directories (EscapeRoute-class).
.claude/hooks/version-guard.py:16.claude/hooks/version-guard.py:18.claude/hooks/version-guard.py:20src/llm_router/tools/subscription.py:151
Fix: Resolve to a canonical path and verify containment; reject ../ and symlinks.
Warn
No SSRF sinksguard30 occurrences
Fetching tool-supplied URLs can pivot into internal networks and metadata services.
.claude/hooks/auto-route.py:200.claude/hooks/auto-route.py:560.claude/hooks/auto-route.py:593.claude/hooks/auto-route.py:615
Fix: Allow-list destinations; reject arbitrary/loopback/link-local URLs.
Warn
Dependencies pinned (lockfile)no lockfile found
A lockfile makes installs reproducible and resistant to silent dependency swaps.
Fix: Commit a lockfile (package-lock.json / pnpm-lock.yaml / poetry.lock).
Pass
No dynamic code executionguardno sinks found
eval()/exec()/Function() on tool-derived strings allows arbitrary code execution.
Pass
No unsafe deserializationguardno sinks found
pickle/yaml.load/etc. on untrusted data can execute code.
Pass
No committed secretsguardno secrets found
Hardcoded keys/tokens in published source are live credentials an attacker can use.
Pass
Credentials sourced from environmentreads credentials from environment
Reading secrets from env/secret stores avoids hardcoding them.
Pass
Actively maintainedrecent commits
Unmaintained servers don't receive security fixes.
Pass
Repository not archivedguardactive
Archived repositories will never be patched.
Pass
Declares a licenseMIT
A clear license is required for legal enterprise use.
Pass
Has a security policySECURITY.md present
A SECURITY.md gives a private path to report vulnerabilities.
Pass
Adoption & popularityestablished adoption
A small, capped nudge from stars/downloads — widely-used servers get more eyes on bugs. It can never offset a real security failure.
Not checked
No known-vulnerable dependenciesno lockfile found
Runtime dependencies (parsed from the lockfile) are scanned against OSV.dev for published CVEs. Advisory: flagged dependencies lower the score but don't hard-cap it, since transitive reachability is unproven.
Not checked
Signed releasesnot evaluated
Signed releases let consumers verify artifacts weren't tampered with.
N/A
No install/post-install scriptsguardno published package
install hooks run arbitrary code on every consumer at install time.
N/A
Package name not typosquattingguardno published package
Names mimicking popular packages are a common malware delivery vector.
N/A
Published with provenanceno published package
Build provenance attests the artifact was built from the claimed source by CI.
N/A
Established maintainerno published package
Brand-new / single anonymous maintainers raise takeover and malware risk.

Transport & Trust Model

Warn
Execution Sandboxingruns natively (no container image)
A container/sandbox image limits blast radius; a server that runs natively has full host access.
Fix: Ship a Dockerfile/Containerfile (or document a sandboxed run) so the server runs isolated.
Warn
Network Exposurebinds 0.0.0.0
Binding 0.0.0.0 or exposing debug inspectors widens the attack surface.
Fix: Bind to 127.0.0.1 by default; never ship open debug endpoints.
N/A
Transport Encryption (TLS)guardno remote endpoints
Plaintext HTTP exposes traffic and bearer tokens to interception.
N/A
IAM / Authentication Scopingno remote endpoints
OAuth 2.1 / Protected Resource Metadata gates who can invoke tools.
N/A
Live Endpoint Reachablenot dynamically scanned
A dynamic scan connected to the declared remote endpoint and it responded — verified live, not a dead URL.
N/A
Authentication Enforced (live)not dynamically scanned
If the server declares auth is required, it must actually reject anonymous clients. Serving tools to unauthenticated callers is a real exposure.

Embed this score

Add the live badge to your README — it updates automatically on every rescan.

markdown

[![Canopii Trust Score](https://index.canopii.dev/api/badge/ypollak2/llm-router)](https://index.canopii.dev/server/ypollak2/llm-router)

html

<a href="https://index.canopii.dev/server/ypollak2/llm-router"><img src="https://index.canopii.dev/api/badge/ypollak2/llm-router" alt="Canopii Trust Score" /></a>

Versions

Version	Score	Status	Published
vmain@72dd582latest	15F	scored	8/5/2026

Wondering how this compares? The MCP Security Index tracks grade distribution, committed secrets, and missing authentication across the whole ecosystem, refreshed monthly.