Metal Mantra / AGENT INTELLIGENCEPublic evidence reportAUTOMATED SIGNAL. NOT CERTIFICATION.
PUBLIC REPORT · ADDED BY METAL MANTRA / AGENT SIGNAL v0.2

claude-code-router.

Scanned repository says: Local Claude Code Router gateway with CLI and web management UI.

Metal Mantra scanned this public repository on its own initiative; the maintainer did not submit it. Maintainers: scan the repository yourself to take this report over, or contact us.

Inspect GitHub source

37.6k starsMITpushed 2d ago

0community interest

Votes show community interest, not safety. They never change this score.

AUTOMATED SIGNAL70/100BBBNot security certification
START HERE

Critical findings need attention.

Critical finding · details withheld for 30 days

Inspect the findings
WHAT THIS DOES NOT ESTABLISH

Runtime safety, real-world agent capability, fitness for your use case or independent certification.

Scan scope200 / 335Partial eligible-file selection · not the entire repository
Recorded findings12Heuristic matches requiring human review
SnapshotOct 12, 2026UTC · engine 0.4.0
DNS at scan timeUnverifiedDomain control is not security certification
01 / KNOW THE REPOSITORY

What the source
actually tells us.

Structured, cited information from the scanned archive. Repository-authored claims are labeled and never treated as verified capabilities.

INSPECTED SOURCE200 / 335Partial selection
READMEReadRepository-authored information
MANIFESTS2LICENSE, package.json

Who it is for

  • Stated purpose · manifest declares · unreviewed

    Local Claude Code Router gateway with CLI and web management UI.

    package.json:6

What it can do

  • Stated capability · repository says · unreviewed

    Manage all agents and providers together instead of maintaining a separate model configuration for every client.

    README.md:34
  • Stated capability · repository says · unreviewed

    Switch providers or models without changing your workflow or repeatedly editing agent configuration files.

    README.md:35
  • Stated capability · repository says · unreviewed

    Keep requests running with retries, credential pools, key rotation, and ordered fallback models.

    README.md:36

What adoption takes

  • Stated prerequisite · manifest declares · unreviewed

    Manifest declares Node.js >=22 as a requirement.

    package.json:27
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on openai.

    package.json:85
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on @the-next-ai/ai-gateway.

    package.json:80
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on @the-next-ai/bot-gateway-sdk.

    package.json:81
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on better-sqlite3.

    package.json:82
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on electron-updater.

    package.json:83
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on node-forge.

    package.json:84

Limits and terms

  • Declared license · manifest declares · unreviewed

    Manifest declares MIT as its license.

    package.json:5

Observed technical context

TypeScript · 200 selected filesModel API reference · static onlyTool-calling reference · static only

These are references in selected source files, not proof that a feature works at runtime.

Read from commit 057abaa at Oct 12, 2026, 5:11 AM UTC. Source links open that exact commit. Repository statements are unreviewed and do not affect the score.

02 / FINDINGS FIRST

What needs
a closer look.

Critical details are withheld publicly for the first 30 days after a scan. A matched pattern is a lead for investigation, not a confirmed vulnerability.

Dependencies: 361 exact runtime versions from package-lock.json checked against OSV.dev on Oct 12, 2026; 11 with known advisories. Reachability is not checked.

12 findings
CRITICAL

Critical finding · details withheld for 30 days

SEC001 · Security & privacy

Details are withheld from public view for 30 days after the scan. The owner can see them in full.

SUGGESTED ACTION

Review the private assessment and address the finding.

[location embargoed] · location unavailable
MAJOR

Model call without fallback

EFF001 · Token & cost efficiency

A model call has no visible fallback. If the provider fails or is rate limited, the whole agent fails with it.

SUGGESTED ACTION

Configure a secondary model or explicit fallback path for provider failures.

packages/core/src/mcp/toolhub-mcp.ts:1649
MAJOR

Domain ownership not verified

TRUST001 · Entity trust

Metal Mantra could not confirm that the owner controls the stated domain. The domain may belong to someone else.

SUGGESTED ACTION

Verify the domain using the Metal Mantra DNS TXT challenge.

ccrdesk.top · location unavailable
MAJOR

Dependency with a high-severity advisory

DEP001 · Security & privacy

basic-ftp 5.3.1 (npm) has a known advisory: GHSA-c475-qrg2-pj4r (highest severity high). basic-ftp: Quadratic-time CPU denial of service in Client.list() Unix directory-listing parser (RE_LINE backtracking)

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

package-lock.json:2951
MAJOR

Dependency with a high-severity advisory

DEP001 · Security & privacy

brace-expansion 5.0.9 (npm) has known advisories: GHSA-6j4f-fj2g-mc7p, GHSA-q2hr-2g5m-vwhr, GHSA-qhr7-859c-m2p7 (highest severity high). brace-expansion: DoS via uncontrolled recursion in parseCommaParts causing stack exhaustion

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

package-lock.json:6255
MAJOR

Dependency with a high-severity advisory

DEP001 · Security & privacy

braces 3.0.3 (npm) has a known advisory: GHSA-vfj7-8cjw-p6xm (highest severity high). braces vulnerable to stack-exhaustion denial of service through deeply nested patterns

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

package-lock.json:3036
MINOR

Raw model text returned

SCH002 · Schema & tooling

The code returns the model's raw text. Output that was never parsed or validated can pass mistakes straight to users or other systems.

SUGGESTED ACTION

Parse and validate the result before returning it.

packages/core/src/providers/probe.ts:1923
MINOR

Privacy Policy link not confirmed

TRUST003 · Entity trust

No privacy policy link was found on the stated homepage. Buyers cannot see how the vendor handles their data.

SUGGESTED ACTION

Expose a clear Privacy Policy link on the official homepage.

ccrdesk.top · location unavailable
MINOR

Terms link not confirmed

TRUST004 · Entity trust

No terms link was found on the stated homepage. Buyers cannot see the conditions that apply to using the service.

SUGGESTED ACTION

Expose a clear Terms link on the official homepage.

ccrdesk.top · location unavailable
MINOR

Dependency with a known advisory

DEP002 · Security & privacy

fastify 5.8.5 (npm) has known advisories: GHSA-3m5p-2c4r-xxw2, GHSA-4mh8-r7rc-xpvc, GHSA-667r-xxjv-c9mm, GHSA-9q9j-q6p8-xq58, GHSA-hwr6-493r-vm6h (highest severity moderate). fastify vulnerable to X-Forwarded-* spoofing under trustProxy hop-count

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

package-lock.json:4784
MINOR

Dependency with a known advisory

DEP002 · Security & privacy

ip-address 10.5.0 (npm) has known advisories: GHSA-2vr4-cq9g-pvrc, GHSA-h3mg-xc3c-68pw, GHSA-j6r3-76f7-8jcv, GHSA-rpw4-54j3-4h4q (highest severity moderate). ip-address: no classifier recognizes the NAT64 local-use range 64:ff9b:1::/48, allowing SSRF and trust-boundary bypass

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

package-lock.json:5480
MINOR

Dependency with a known advisory

DEP002 · Security & privacy

moment 2.30.1 (npm) has a known advisory: GHSA-4p3w-j4w9-5jqw (highest severity moderate). moment vulnerable to Path Traversal via crafted non-string locale name

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

package-lock.json:6338
03 / EVIDENCE & LIMITS

The boundary
is part of the result.

What was scanned
200 of 335 eligible files · Partial selection.
Supported static source patterns and domain checks; no runtime execution.
What remains unknown
Unscanned files, external dependencies, production configuration, actual agent behavior and evidence beyond the configured checks.
Source location
Links open the current repository HEAD. Source may have changed since this snapshot.
Something looks wrong?
Tell us if a finding, scope or claim on this report needs a correction. Report a problem with this report
Entity trust · 15% of v0.2
Includes DNS ownership, HTTPS and policy evidence. Verification is domain control, not a security certificate.
DNS: unverifiedHTTPS: availablePrivacy: not confirmedTerms: not confirmed
04 / THE METHOD BEHIND THE NUMBER

Open the
calculation.

Each pillar starts at 100. Rule deductions reduce its score; weights determine the overall contribution.

01

Security & privacy

7 findings · 25% weight
40/10010.0 pts
02

Guardrails & loop control

0 findings · 25% weight
100/10025.0 pts
03

Schema & tooling

1 findings · 20% weight
92/10018.4 pts
04

Token & cost efficiency

1 findings · 15% weight
86/10012.9 pts
05

Entity trust

3 findings · 15% weight
25/1003.8 pts
Inspect the current standard
USER REPORTS

Did claude-code-router work for people?

No user reports yet.

Each report is one signed-in GitHub account saying what happened. We do not verify that the account ran the agent, and reports never change the automated score or grade. For a security problem, use the disclosure page instead of a public note.

Sign in with GitHub to add a report

SHARE THE EVIDENCE

A signal.
Not a seal.

Share the full report so its scope and limits travel with the score.

Metal Mantra automated signal 70/100, not certified