CanopiiCanopiiAll serversEnterprise →

hol-guard MCP Server Security Report

io.github.hashgraph-online/hol-guard

Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.

Security Trust Score
Grade A · Strong posture
Tier 1 · Public sourceHigh confidence · 92%latest v3.8.1 Repository
Declared MCP capabilities
ResourcesPrompts

Run it securely

Host io.github.hashgraph-online/hol-guard in a governed environment — SSO in front, every tool call attributed and audited.

Are you the maintainer?

Verify with GitHub to get alerted whenever hashgraph-online/hol-guard changes score — and claim the badge for your README.

Claim this server

The short answer

Is hol-guard safe to use?
hol-guard scores 92/100 (grade A) on the Canopii Trust Index — strong posture. It passes 18 of the 25 security controls that apply to it, with no confirmed security failures.
How reliable is the security score for hol-guard?
We could evaluate 92% of the controls that apply to hol-guard. 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 hol-guard 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.
Reputation677stars111forks112open issues1d agolast commit<1yage

Security controlslatest scored version v3.8.1

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
    Tool Definition Integrityguardtool definitions stable; no risky changes in version history

    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.

  • Pass
    User-in-the-Loop / Approval Scopeguardno destructive tool scope

    No over-broad or destructive tools (arbitrary shell, bulk-delete) that warrant human approval.

Application Security Checks

  • Warn
    No path traversalguard35 occurrences

    Naive path checks let tools read/write outside intended directories (EscapeRoute-class).

    dashboard/e2e/installed-command-activity.spec.ts:18dashboard/e2e/installed-extension-control-center.spec.ts:109dashboard/e2e/static-server.mjs:29dashboard/src/about/about-content.test.ts:104

    Fix: Resolve to a canonical path and verify containment; reject ../ and symlinks.

  • Warn
    No SSRF sinksguard1 occurrence (build/test paths only)

    Fetching tool-supplied URLs can pivot into internal networks and metadata services.

    ci/native_runtime/installed_hook_client.py:52

    Fix: Allow-list destinations; reject arbitrary/loopback/link-local URLs.

  • Warn
    Established maintainerrecently published

    Brand-new / single anonymous maintainers raise takeover and malware risk.

    Fix: Publish under an established account/org; add multiple maintainers.

  • Pass
    No command-injection sinksguardno sinks found

    Untrusted tool input reaching a shell yields remote code execution.

  • 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
    No known-vulnerable dependencies68 runtime deps, no known CVEs

    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.

  • Pass
    Dependencies pinned (lockfile)lockfile present

    A lockfile makes installs reproducible and resistant to silent dependency swaps.

  • Pass
    Package name not typosquattingguarddistinct package name

    Names mimicking popular packages are a common malware delivery vector.

  • Pass
    Actively maintainedrecent commits

    Unmaintained servers don't receive security fixes.

  • Pass
    Repository not archivedguardactive

    Archived repositories will never be patched.

  • Pass
    Declares a licenseApache-2.0

    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
    Signed releasesnot evaluated

    Signed releases let consumers verify artifacts weren't tampered with.

  • Not checked
    No install/post-install scriptsguardnot determinable from PyPI metadata

    install hooks run arbitrary code on every consumer at install time.

  • Not checked
    Published with provenancenot determinable

    Build provenance attests the artifact was built from the claimed source by CI.

Transport & Trust Model

  • 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.

  • Pass
    Execution Sandboxingcontainerized

    A container/sandbox image limits blast radius; a server that runs natively has full host access.

  • 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.

Canopii Trust Score badge preview
markdown[![Canopii Trust Score](https://index.canopii.dev/api/badge/io.github.hashgraph-online/hol-guard)](https://index.canopii.dev/server/io.github.hashgraph-online/hol-guard)
html<a href="https://index.canopii.dev/server/io.github.hashgraph-online/hol-guard"><img src="https://index.canopii.dev/api/badge/io.github.hashgraph-online/hol-guard" alt="Canopii Trust Score" /></a>

Versions

VersionScoreStatus
v3.8.1latest92Ascored
v3.7.492Ascored
v3.6.392Ascored
v3.5.092Ascored
v3.3.192Ascored
v3.1.192Ascored
v3.0.19388Bscored
v3.0.19288Bscored
v3.0.19088Bscored
v3.0.18988Bscored
v3.0.18188Bscored
v3.0.17988Bscored
v3.0.16688Bscored
v3.0.16088Bscored
v3.0.15688Bscored
v3.0.14688Bscored
v3.0.14488Bscored
v3.0.13188Bscored
v3.0.11388Bscored
v3.0.10488Bscored
v3.0.8288Bscored
v3.0.6588Bscored
v3.0.5188Bscored
v3.0.4288Bscored
v3.0.4188Bscored
v3.0.2388Bscored
v3.0.1888Bscored
v3.0.1588Bscored
v3.0.388Bscored
v3.0.0a27586Bscored
v3.0.0a25986Bscored
v3.0.0a24286Bscored
v3.0.0a23186Bscored
v3.0.0a22886Bscored
v3.0.0a21986Bscored
v3.0.0a21586Bscored
v3.0.0a20986Bscored
v3.0.0a20186Bscored
v3.0.0a18886Bscored
v3.0.0a15685Bscored

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