LLM Guard
Website
The Security Toolkit for LLM Interactions
Is LLM Guard safe? Thin or incomplete trust evidence. Review carefully before production use.
Compare LLM Guard
How does it stack up against its Security & Guardrails neighbours?
Pick any agent to compare →In detail: LLM Guard scores 53.6/100 (Grade C), ranked #852 of 1371 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 5.4/10; 60% of recent commits are signed; no published advisory affects its latest release (llm-guard); last pushed 2026-07-08. Every point is earned from checkable signals — never paid placement. How scoring works →
How LLM Guard could raise its score
Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.
- Publish build provenance for its packagesPyPI Trusted Publishing attestations +14.6 → 68.2 B · #7 of 26
- Raise the OSSF Scorecard from 5.4 to 9.0lowest checks: CI-Tests 0, CII-Best-Practices 0, Contributors 0 +7.5 → 61.1 C · #10 of 26
- Sign every commit60% signed today +2.0 → 55.6 C · #14 of 26
Chain of custody
Scanners check what the code says. This traces who ships LLM Guard and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.
-
Source Partly signed
github.com/protectai/llm-guard, MIT, last pushed 2026-07-08. 60% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.
-
Review and release Mixed
OpenSSF Scorecard rates the repository's practices 5.4/10 (scanned Oct 4, 2026). The checks that decide who can get a change released:
- Code Review8
- Branch Protection1
- Signed Releasesn/a
- Dangerous Workflow10
- Token Permissions0
- Pinned Dependencies0
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 1CI-Tests 0CII-Best-Practices 0Code-Review 8Contributors 0Dangerous-Workflow 10Dependency-Update-Tool 10Fuzzing 0License 10Maintained 0Packaging -1Pinned-Dependencies 0SAST 7Security-Policy 10Signed-Releases -1Token-Permissions 0Vulnerabilities 10 -
Published packages Not linked
- PyPI llm-guard Source link isn't a GitHub repo No build attestation
Without a build attestation, nothing proves the published files were built from this repository.
-
What you install today No known advisories
Latest release checked: llm-guard 0.3.16. No published advisory affects it (OSV, checked 2026-10-09).
Changes to this chain
No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of LLM Guard.
Evidence behind this score
Coverage A: 4 of 5 independent evidence types found.
- GitHub repository data
- Package downloads
- Supply-chain checks
- Public actions (missing)
- Community mentions
Verify this score yourself
Every build re-issues LLM Guard’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.
What this score doesn’t check
It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.
How LLM Guard compares in Security & Guardrails
- #13 open-kritt 55.9 +2.3
- #14 CyberStrike 53.9 +0.3
- #15 LLM Guard 53.6 this agent
- #16 Cybermes 53.5 −0.1
- #17 Llama Guard 53.2 −0.4
Bars show each HVTrust score; the tick marks LLM Guard’s 53.6.
Where the 53.6 comes from
HVTrust dimensions vs the Security & Guardrails average
53.6 / 100 · 100.0% confidenceLLM Guard Security & Guardrails average (26 agents)
Quick Trust Read
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
Activity & Reach
Analysis
Activity Inputs
45.6 / 100Common questions about LLM Guard
Does LLM Guard publish package provenance?
Does LLM Guard have an OpenSSF Scorecard?
Is LLM Guard actively maintained?
What license does LLM Guard use?
Are LLM Guard's commits signed?
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
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 signal live
- External deps live
- Tool / plugin surface live
- Package provenance drift live
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.
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.
Reputation Timeline
Signal history
Embed Badge Badge guide for maintainers →
For maintainers
[](https://hvtracker.net/agents/llm-guard)
<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
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 v4.4 · Raw JSON