Is LLM Guard safe to use?

LLM Guard has an HVTrust score of 54.3/100 (Grade C), ranked #415 of 1308 tracked AI agent projects. This score reflects verifiable supply-chain integrity, transparency, maintenance, and adoption signals.

What is the trust score for LLM Guard?

LLM Guard scores 54.3/100 on HVTracker's evidence-weighted HVTrust scale. It has 3.2k GitHub stars and is categorized under Security & Guardrails.

LLM Guard

protectai/llm-guard

The Security Toolkit for LLM Interactions

Security & Guardrails Python Grade C Needs review MIT

54.3/100

Rank #415 of 1308

Compare LLM Guard

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

Pick any agent to compare →

Thin or incomplete trust evidence. Review carefully before production use.

Open compare tool Suggest correction

Listing state

Needs review

Evidence coverage

Grade A · 4/5 signals

Last push

2026-07-08 · 48d ago

Recent change

Rank +3

Is LLM Guard safe? LLM Guard scores 54.3/100 (Grade C), ranked #415 of 1308 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 5.6/10; recent commits are unsigned; last pushed 2026-07-08. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Security & Guardrails

#11 PentestAgent — 55.7 (C) → #12 Agentic Security — 54.9 (C) → #14 Llama Guard — 53.2 (C) → #15 HexStrike AI — 45.8 (D) →

Quick Trust Read

What Would Improve It

Publish package provenance or release attestations for stronger supply-chain evidence.

Recent Changes

2026-08-25

Rank Moved

Rank rose 16 spots (#431 → #415)

2026-08-24

Rank Moved

Rank dropped 17 spots (#414 → #431)

2026-08-22

Rank Moved

Rank rose 16 spots (#430 → #414)

Maintainer Checklist

Raise Scorecard signals Current OSSF Scorecard is 5.6/10. Tighten the weakest checks to improve public safety evidence.

Publish provenance Add package provenance or release attestations so users can verify where shipped artifacts came from.

Increase signed commits Raise the share of verified-signed commits to make maintainer identity and release history easier to trust.

Refresh maintenance signals The repo was last pushed 48 days ago. Fresh activity helps separate stable projects from stale ones.

Review Flags

[5.1] repository is archived

Compare with another agent Get email alerts for LLM Guard View Security & Guardrails Report missing data

51.8

Activity sub-score · out of 100

#13

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 C reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage A is separate — it grades how many independent signal types back the score (4 of 5), so a high score on thin evidence stays visible. Full methodology →

Rank Trend

2026-08-11 2026-08-25

Activity & Reach

Stars

3.2k

Forks

446

Last Push

2026-07-08

48 days ago

Commits (4 wk)

Downloads (7d)

55,564

pypi

HN mentions (30d)

Open Issues

Rank Change

▲16

was #431

Analysis

HVTrust Dimensions vs Security & Guardrails

54.3 / 100 · 100.0% confidence

LLM Guard Security & Guardrails average (20 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits

7.0 / 25

2.1 below avg 9.1

Identity / Provenance60% listing status · 40% build provenance

10.8 / 18

1.4 below avg 12.2

Transparency50% declared license · 50% OSSF Scorecard

13.3 / 17

1.4 above avg 11.9

Maintenance60% last-push freshness · 40% commit activity

8.8 / 20

7.5 below avg 16.3

AdoptionLog-scaled stars · package downloads

14.7 / 20

4.7 above avg 10.0

Activity Inputs

51.8 / 100

StarsRepository reach

21.0 / 30

FreshnessLast push recency

18.3 / 25

ActivityRecent commits

0.0 / 25

CommunityFork signal

12.3 / 20

Supply Chain Trust

Package Provenance

None

No package attestations found

OSSF Scorecard

5.6 / 10

OpenSSF Scorecard · scanned Aug 23, 2026

Signed Commits

—

Unable to query

Binary-Artifacts 10

Branch-Protection 1

CI-Tests 4

CII-Best-Practices 0

Code-Review 8

Contributors 0

Dangerous-Workflow 10

Dependency-Update-Tool 10

Fuzzing 0

License 10

Maintained 0

Packaging -1

Pinned-Dependencies 0

SAST 8

Security-Policy 10

Signed-Releases -1

Token-Permissions 0

Vulnerabilities 10

Is LLM Guard safe?

Public trust evidence for LLM Guard is thin: several supply-chain signals are missing or weak. This does not mean the project is unsafe — it means an outside observer cannot easily verify the usual integrity checks. Treat with extra scrutiny.

Does LLM Guard publish package provenance?

No published build provenance is currently detected for LLM Guard. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.

Does LLM Guard have an OpenSSF Scorecard?

LLM Guard has an OpenSSF Scorecard score of 5.6/10. 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 LLM Guard actively maintained?

Slowing down. Last push was 48 days ago — keep an eye on whether activity resumes.

What license does LLM Guard use?

LLM Guard ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.

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.

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

None detected

No MCP server signal detected.

Detailed evidence is not shown in the public view.

External Service Dependencies

None detected

No clear third-party provider dependency detected.

Credential signal: No explicit API-key/config marker detected.

Tool / Plugin Surface

high confidence

Declared

Declared plugin/integration surface detected.

Detailed evidence is not shown in the public view.

Package Provenance Drift

low confidence

Unknown

Package source metadata is missing or inconclusive

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 LLM 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.

2026-07-08

Activity Resumed

Activity resumed

Maintain LLM Guard?

For maintainers

HVTrust scores LLM 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

2026-08-25

Rank Moved

Rank rose 16 spots (#431 → #415)

2026-08-24

Rank Moved

Rank dropped 17 spots (#414 → #431)

2026-08-22

Rank Moved

Rank rose 16 spots (#430 → #414)

2026-08-19

Rank Moved

Rank dropped 14 spots (#414 → #428)

2026-08-17

Rank Moved

Rank rose 10 spots (#425 → #415)

2026-08-16

Rank Moved

Rank dropped 11 spots (#414 → #425)

2026-08-13

Rank Moved

Rank dropped 17 spots (#396 → #413)

2026-08-12

Rank Moved

Rank rose 12 spots (#408 → #396)

2026-08-10

Warning Issued

Warning: eligibility issues detected

2026-08-10

Rank Moved

Rank dropped 19 spots (#388 → #407)

2026-08-09

Warning Cleared

Warning cleared: eligibility issues resolved

2026-08-08

Rank Moved

Rank dropped 108 spots (#278 → #386)

2026-07-15

Warning Issued

Warning: eligibility issues detected

2026-07-15

Rank Moved

Rank dropped 11 spots (#218 → #229)

2026-07-14

Warning Cleared

Warning cleared: eligibility issues resolved

2026-07-14

Rank Moved

Rank dropped 15 spots (#203 → #218)

2026-07-13

Warning Issued

Warning: eligibility issues detected

2026-07-13

Rank Moved

Rank dropped 25 spots (#178 → #203)

2026-07-12

Warning Cleared

Warning cleared: eligibility issues resolved

2026-07-09

Warning Issued

Warning: eligibility issues detected

2026-07-09

Rank Moved

Rank rose 13 spots (#185 → #172)

2026-07-08

Activity Resumed

Activity resumed

2026-07-08

Grade Changed

Trust grade D → C

2026-07-08

Rank Moved

Rank rose 68 spots (#253 → #185)

2026-07-08

HVTrust Changed

HVTrust up 12.0pts (45.8 → 57.8)

2026-07-08

Activity Score Changed

Activity score up 25pts (33 → 58)

2026-06-24

Rank Moved

Rank dropped 31 spots (#221 → #252)

2026-06-23

Rank Moved

Rank dropped 16 spots (#205 → #221)

2026-06-20

Rank Moved

Rank dropped 13 spots (#174 → #187)

2026-06-18

Rank Moved

Rank dropped 12 spots (#158 → #170)

2026-06-10

Grade Changed

Trust grade C → D

2026-06-01

Rank Moved

Rank dropped 17 spots (#111 → #128)

2026-05-29

HVTrust Changed

HVTrust up 9.9pts (39.0 → 48.9)

GitHub → PyPI: llm-guard

Embed Badge Badge guide for maintainers →

For maintainers

Markdown:
            [![HVTrust](https://hvtracker.net/badge/llm-guard.svg)](https://hvtracker.net/agents/llm-guard)
            
HTML:
            <a href="https://hvtracker.net/agents/llm-guard"><img src="https://hvtracker.net/badge/llm-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 · Algolia HN Search API
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.3 · Raw JSON