updated 2026-09-04 23:32 UTC

HOL Guard

hashgraph-online/hol-guard

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers

Security & Guardrails Python Grade A Listed Apache-2.0
86.5/100
Rank #44 of 1320
Compare HOL Guard

How does it stack up against its Security & Guardrails neighbours?

Pick any agent to compare →

Strong public trust posture, backed by multiple independent signals.

Open compare tool Suggest correction
Listing state
Listed
Evidence coverage
Grade B · 3/5 signals
Last push
2026-09-04 · 0d ago
Recent change
Mcp Status Changed +1

Is HOL Guard safe? HOL Guard scores 86.5/100 (Grade A), ranked #44 of 1320 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; OSSF Scorecard rates its supply-chain practices 7.0/10; 100% of recent commits are signed; last pushed 2026-09-04. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Security & Guardrails

#2 Guardrails AI — 81.2 (A) → #3 NeMo Guardrails — 72.7 (B) → #4 Snyk Agent Scan — 64.5 (C) → #5 SkillSpector — 64.1 (C) →

Quick Trust Read

What Would Improve It
Improve adoption to lift the weakest part of the trust profile.
Recent Changes
2026-09-02
Mcp Status Changed
Detected MCP server support changed: implemented → declared
2026-09-02
Rank Moved
Rank dropped 16 spots (#27 → #43)
2026-08-16
Newly Listed
First tracked at rank #20
Maintainer Checklist
Keep signals current Trust posture is already in a healthy range. The main job is to keep provenance, maintenance, and public evidence fresh.
Compare with Guardrails AI Get email alerts for HOL Guard View Security & Guardrails Report missing data
73.3
Activity sub-score · out of 100
#1
In Security & Guardrails

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade A reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage B is separate — it grades how many independent signal types back the score (3 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-09-04 23:32 UTC · Repo last pushed today

Rank Trend

2026-08-16 2026-09-04

Activity & Reach

Stars
549
Forks
29
Last Push
2026-09-04
today
Commits (4 wk)
1171
Downloads (7d)
23,792
pypi
HN mentions (30d)
—
Open Issues
4
Rank Change
=
was #44

Analysis

HVTrust Dimensions vs Security & Guardrails

86.5 / 100 · 100.0% confidence

HOL Guard Security & Guardrails average (22 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
21.2 / 25
11.0 above avg 10.2
Identity / Provenance60% listing status · 40% build provenance
18.0 / 18
5.9 above avg 12.1
Transparency50% declared license · 50% OSSF Scorecard
14.4 / 17
1.8 above avg 12.6
Maintenance60% last-push freshness · 40% commit activity
20.0 / 20
3.6 above avg 16.4
AdoptionLog-scaled stars · package downloads
12.4 / 20
2.8 above avg 9.6

Activity Inputs

73.3 / 100
StarsRepository reach
16.4 / 30
FreshnessLast push recency
25.0 / 25
ActivityRecent commits
25 / 25
CommunityFork signal
6.9 / 20

Supply Chain Trust

Package Provenance
Verified
pypi attestation
OSSF Scorecard
7.0 / 10
OpenSSF Scorecard · scanned Sep 4, 2026
Signed Commits
100%
of last 100 commits verified
Binary-Artifacts 10
Branch-Protection 3
CI-Tests 10
CII-Best-Practices 0
Code-Review 1
Contributors 6
Dangerous-Workflow 10
Dependency-Update-Tool 10
Fuzzing 10
License 10
Maintained 10
Packaging 10
Pinned-Dependencies 8
SAST 10
Security-Policy 10
Signed-Releases 10
Token-Permissions 0
Vulnerabilities 0

Is HOL Guard safe?

Public supply-chain signals for HOL Guard are strong: it has multiple independent trust indicators in place. This does not replace your own security review, but HOL Guard carries less obvious unverified-evidence risk than projects with thin signals.
Does HOL Guard publish package provenance?
Yes. HOL Guard's package releases carry build provenance attestations, which cryptographically link the published package back to its source repository and CI workflow.
Does HOL Guard have an OpenSSF Scorecard?
HOL Guard has an OpenSSF Scorecard score of 7.0/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.
Is HOL Guard actively maintained?
Actively maintained. The repository was pushed to within the last 1 day(s).
What license does HOL Guard use?
HOL Guard ships under Apache-2.0. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are HOL Guard's commits signed?
100% of the last 100 commits to HOL Guard are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.

Compare HOL Guard head-to-head

HOL Guard vs Guardrails AI → HOL Guard vs NeMo Guardrails → HOL Guard vs Snyk Agent Scan →

AI agent surface

MCP, providers, tool surface
Scored in HVTrust

These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →

MCP Server Support
medium confidence
Declared
MCP support appears present, but direct server implementation is less certain.
Detailed evidence is not shown in the public view.
External Service Dependencies
high confidence
3 detected
Public provider/service dependencies detected.
Credential signal: API keys or service config markers documented.
Tool / Plugin Surface
high confidence
Declared
Declared plugin/integration surface detected.
Detailed evidence is not shown in the public view.
Package Provenance Drift
high confidence
Match
Published package metadata matches the tracked repo
Detailed evidence is not shown in the public view.
  • MCP signal live
  • External deps live
  • Tool / plugin surface live
  • Package provenance drift live
How this surface has changed

Detected changes to HOL Guard's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.

2026-09-02
Mcp Status Changed
Detected MCP server support changed: implemented → declared

Maintain HOL Guard?

For maintainers

HVTrust scores HOL Guard from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history
Listed 1Rank 1MCP 1
2026-09-02
Mcp Status Changed
Detected MCP server support changed: implemented → declared
2026-09-02
Rank Moved
Rank dropped 16 spots (#27 → #43)
2026-08-16
Newly Listed
First tracked at rank #20
GitHub → PyPI: hol-guard

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 86.5 Grade A
Markdown:
[![HVTrust](https://hvtracker.net/badge/hol-guard.svg)](https://hvtracker.net/agents/hol-guard)
HTML:
<a href="https://hvtracker.net/agents/hol-guard"><img src="https://hvtracker.net/badge/hol-guard.svg" alt="HVTrust"></a>

Other agents in Security & Guardrails

Data sources
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.3 · Raw JSON