pkgxray

Supply-chain security for AI agents, npm packages, and Model Context Protocol (MCP) servers.

Analyze packages before you install them. Zero-dependency Node, runs entirely on your machine, never executes untrusted code.

Static analysis · Supply-chain intelligence · Prompt-injection detection · MCP security · SAFE / REVIEW / BLOCK

_{Real runs: guard clears express@4.21.0, then blocks a sample modeled on the 2024 @solana/web3.js compromise. ▶ 60-second walkthrough}

Quick start

npm install -g pkgxray        # or zero-install: npx pkgxray …

pkgxray guard npm:express@4.21.0

Decision: **SAFE**
Grade: **A+** (99/100)

No high- or medium-risk indicators were found in the provided evidence.

Notes:
- **INFO npm-vs-github-clean** — npm tarball matches the linked GitHub repo
  at the published version. (15/16 files match GitHub @4.21.0)
…

_{Real output, abridged. A BLOCK verdict instead lists every finding with the file and evidence that produced it.}

Point it at a package, get a verdict with cited evidence — before a single line of that package runs. guard stages the package in a sandboxed quarantine, audits the staged copy, and only promotes it when policy allows. It never runs npm install, lifecycle scripts, build steps, or package code.

Why pkgxray?

AI coding assistants install packages and connect to MCP servers at machine speed, often without a human ever reading the code — and the registry they pull from is under industrial-scale attack: roughly 455,000 malicious npm packages were published in 2025, one every ~20 seconds by Q4 (Sonatype). Traditional antivirus inspects what executes; pkgxray inspects what gets installed.

npm audit and OSV-Scanner answer an essential question — does this package have a known CVE? — and pkgxray asks it too (via OSV, before anything downloads). But a freshly trojaned package has no CVE yet, so pkgxray also analyzes trust: what the code actually does, whether the published npm artifact matches the tagged GitHub source, whether the provenance attestation is consistent with the claimed repository, and whether the docs carry a prompt-injection payload aimed at the agent reading them.

It is intentionally conservative: verdicts come from deterministic heuristics (no LLM in the verdict path, so injected text can't steer them), only citable evidence is reported, and the zero-heuristic-false-block calibration on the top-1000 most-downloaded packages is regression-gated in CI. That claim is scoped to the most-installed set — it is not a claim of zero false blocks on every package; the newer MCP/agent-tooling ecosystem is over-blocked and being reconciled per-case (details).

What it catches

Threat	Coverage	How pkgxray sees it
Credential theft	✅	reads of .ssh / .aws / .npmrc / .env / keychains / wallets, incl. split-fragment paths (".s"+"sh")
Prompt injection	✅	tiered detection in docs, comments, metadata; deterministic verdict path can't be steered
Unicode smuggling	✅	invisible tag-block characters + Trojan Source bidi / zero-width
Base64 payloads	✅	encoded envelopes in docs/comments; blobs decoded into computed-arg eval / new Function / child_process
Exfiltration & loaders	✅	cross-file correlation: stage-2 loaders, curl | sh, process.env harvesting near a network sink, EtherHiding
Persistence	✅	writes to shell rc files, cron, launch agents
Obfuscation	✅	packed blob + computed-arg execution; minification alone is deliberately not flagged
Known CVEs	✅	OSV batch pre-check before download; never mutable by config
Trojaned updates / maintainer takeover	✅	recheck verdict-drift + version-drift monitoring
Artifact divergence	✅	published npm tarball diffed against the tagged GitHub source
MCP capability abuse	✅	capability-surface mismatch in the manifest audit (a get_weather that also takes a command)
Runtime tool drift	✅	mcp-proxy re-audits on tools/list_changed; pinned-manifest drift is denied
Dependency confusion / typosquats	◑	callback beacons, repo-mismatch and provenance-mismatch signals; no name-similarity heuristic

_{✅ detected · ◑ partial / indirect}

Known blind spot: pkgxray reasons about bytes in the tarball. A package that downloads its real payload after install can ship a clean tree — pkgxray flags the capability when its shape is unambiguous, but pair it with runtime sandboxing when that risk matters. Full analysis: docs/threat-model.md.

Beyond detection

• Continuous monitoring — pkgxray recheck diffs installed deps against a stored verdict baseline and pre-vets newer versions
• MCP vetting — pkgxray mcp audits a server's tool manifest before you connect; --pin / --recheck catch the rug-pull; pkgxray-mcp gives any agent the audit tools directly
• Runtime gate — pkgxray mcp-proxy wraps a live MCP server on the wire: denied tools stripped, ~0.05 µs per-call verdict, injection scan of tool results
• Install gate — a hookshot hook runs guard on every package an agent tries to install, across Claude Code, Cursor, Windsurf, Factory Droid, and Codex (examples/hookshot/)
• Policy engine — one .pkgxray.json read by every surface; tighten freely, every loosening is printed; CVEs can never be allowed away; fail closed
• Opt-in behavioral canary — pkgxray canary runs lifecycle scripts in an OS sandbox with decoy credentials; it can confirm malice, never clear a package

Verdicts

Verdict	Meaning	You should
🟢 SAFE	No high- or medium-risk indicators.	Install. Only safe promotes out of quarantine by default.
🟡 REVIEW	Incomplete evidence, or a privileged capability that needs a human.	Inspect the quarantined copy before promoting.
🔴 BLOCK	High-severity, cited evidence.	Do not install. Every finding names the file and evidence.

Exit codes are stable and CI-friendly: 0 safe/allow · 2 block · 3 review. The full signal-to-severity mapping is in the severity policy.

Usage

Vet an npm package before installing

pkgxray guard npm:some-package@1.2.3 [--format json]
pkgxray guard ./ext --promote-to ./approved/ext   # local dir, promote if policy allows

Vet an MCP server before connecting — full guide: docs/mcp.md

pkgxray mcp --package npm:some-mcp-server@1.4.2 npx some-mcp-server
pkgxray mcp --recheck npx some-mcp-server   # catch the rug-pull

Enforce in CI/CD

pkgxray audit package-lock.json [--deep]    # also: yarn.lock, pnpm-lock.yaml, package.json
npx pkgxray recheck package-lock.json       # scheduled: exits non-zero only on a regression

A ready-made GitHub Actions workflow and the self-hostable cache server (PKGXRAY_CACHE_URL) are in the reference.

Guard AI coding agents

pkgxray is published on the MCP Registry as io.github.adamsjack711-ux/pkgxray. Add it to any MCP client — locally installed (pkgxray-mcp) or zero-install via npx:

{ "mcpServers": { "pkgxray": { "command": "pkgxray-mcp" } } }

{ "mcpServers": { "pkgxray": { "command": "npx", "args": ["-y", "pkgxray", "mcp-server"] } } }

Gate installs with the hookshot integration and wrap MCP servers with pkgxray mcp-proxy.

Configuration

One optional .pkgxray.json, read by every surface. Zero config means maximum strictness.

{
  "policy": "safe-only",              // or "allow-review" (a loosening — warns)
  "failOn": "review",                 // CI exit threshold
  "scanErrorPolicy": "fail-closed",   // a scan that errors → review, never safe

  "allow": [
    { "pkg": "left-pad@1.3.0", "sha256": "e0b0…",
      "reason": "reviewed 2026-07", "expires": "2026-10-01" }
  ]
}

Precedence, mute / mcp blocks, and enforced invariants: docs/configuration.md · .pkgxray.example.json

Demo

The 60-second walkthrough — the SAFE run, the blocked trojan with its exit code, then a lockfile audit:

pkgxray-demo.mp4

_{All captures are real runs — reproduction steps in docs/screenshots/, which also shows the MCP proxy, hookshot install gate, and browser extension in action.}

Comparison

Designed to run alongside npm audit and OSV-Scanner, not replace them — they match dependencies against known vulnerabilities; pkgxray adds the layers they don't attempt:

Capability	npm audit	OSV-Scanner	pkgxray
Known-CVE lookup	✅	✅	✅ (OSV, blocks before download)
Lockfile / project scanning	✅	✅	✅
Registry signature / provenance verification	✅ (npm audit signatures)	—	✅ (sigstore/SLSA + repo cross-check)
Static analysis of package code behavior	—	—	✅
Prompt-injection & Unicode-smuggling detection	—	—	✅
npm ↔ GitHub artifact divergence	—	—	✅
Pre-install quarantine of a single package	—	—	✅
Verdict-drift monitoring vs. a stored baseline	—	—	✅
MCP server vetting & per-call runtime gating	—	—	✅

_{Scoped to npm supply-chain vetting, per each tool's public docs. OSV-Scanner covers many ecosystems beyond npm, which pkgxray does not.}

Architecture

Acquisition (OSV pre-check → fetch) → sandboxed quarantine → static analysis → policy → verdict. The same engine backs every surface: CLI, MCP server, runtime proxy, install hook, browser extension, and CI cache server. Principles: never execute untrusted code · citable evidence only · minimize false positives · fail closed · zero runtime dependencies.

Details: docs/architecture.md · docs/design.md

Performance

• Local static analysis: ~25 ms — a full guard of express is ~1.3–1.5 s cold-cache, almost all network round-trips (Apple M1, Node 26)
• Known-vulnerable packages block at the OSV pre-check, before download
• Calibration (precision, recall, the 0-heuristic-false-block gate on the top-1000 most-downloaded — scope) is measured by a committed benchmark corpus that fails CI when it regresses

Full numbers: docs/reference.md#performance · methodology: docs/benchmark.md

Documentation

Doc	What it covers
architecture.md	Pipeline, surfaces, repo layout
threat-model.md	Scope, blind spots, prompt-injection stance
mcp.md	MCP server, connect-time vetting, runtime proxy
configuration.md	.pkgxray.json schema and invariants
reference.md	Severity policy, recheck, JSON output, cache server
benchmark.md	Calibration benchmark & real-world validation
compatibility.md	The 1.0 compatibility contract
json-schema.md	Full --format json schema

Start at the documentation index. Longer-term plans: adoption playbook and GitHub issues.

Development

npm test                 # zero-dep node --test suite
npm run benchmark        # calibration corpus: precision/recall + 0-false-block gate
npm run build:browser    # build the MV3 browser extension

Security & license

Releases are published to npm with provenance (SLSA attestation), gated on the test suite, the calibration benchmark, and pkgxray's own supply-chain guard. To report a vulnerability in pkgxray itself, see SECURITY.md.

MIT