Skip to content
ai-supply.store
DiscoverCategoriesLeaderboardsCommunityAgent APIFAQ
Sign inSign up free
catalog / Cybersecurity / LLM Guard — Input/Output Security Toolkit
⛨GuardrailCybersecurityFree

LLM Guard — Input/Output Security Toolkit

MIT-licensed security toolkit by ProtectAI that sanitizes LLM prompts and responses — blocking prompt injection, toxic content, PII leakage, and secrets.

@ai-supply
Installs169k
⟳ upstream main@168c103 · updated 18d ago
↗ Source repository
← More CybersecurityCybersecurity leaderboard →How we grade security →Source ↗
✓ Grade A · 100/100 · SafeSecurity assessment
✓No compromise signals18capabilities surfaced7of 20 OWASP controls clear
Low-confidence secret matchSuspicious code patterns · expectedExternal endpoints declared · expectedExternal endpoints declared · expected
scanned 14d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

LLM Guard — Input/Output Security Toolkit

LLM Guard is a comprehensive security layer for LLM-powered applications, providing both input (prompt) and output (response) scanners that can be dropped in-line with any LLM call. It is built and maintained by ProtectAI and is widely used in production AI pipelines.

Key Features

  • Input scanners: prompt injection detector, ban-topics filter, ban-substrings, anonymize (PII), token limit enforcement, regex guardrails
  • Output scanners: no-refusal detector, relevance check, JSON/code validation, sensitive-data redaction, factual consistency
  • Synchronous + async APIs; OpenAI-compatible
  • Integrates with LangChain, LlamaIndex, and bare-metal OpenAI clients
  • Self-hosted — no data leaves your infrastructure

Quick Start

from llm_guard import scan_prompt, scan_output
from llm_guard.input_scanners import PromptInjection, Anonymize
from llm_guard.output_scanners import Sensitive

scanned_prompt, results = scan_prompt(
    scanners=[PromptInjection(), Anonymize()],
    prompt="Ignore previous instructions and...",
)
print(scanned_prompt, results)
npx ai-supply add llm-guard-input-output-security

Curated mirror of the open-source LLM Guard (MIT). Get it from the source.

Rating rank
#1
of 19 in Cybersecurity
Install rank
#4
of 19 in Cybersecurity
Security score
100/100 · A
safe
Security rank
#1
of 19 in Cybersecurity
Installs
169k
cat avg 85k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Cybersecurity leaderboard →
✓ Security: Safe · 100100/100 · grade Ascanned 14d ago
✓ no compromise signals18 risk-surface · 7/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

Control card · high confidence (static)
framework: llm-guardframework: pytestframework: presidioframework: guardrails-aicovers: prompt-injectioncovers: piicovers: toxicitycovers: biascovers: secrets-leakcovers: hallucinationcovers: jailbreak
scan

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications
⚠LLM01Prompt Injectionhigh
Adversarial instructions embedded in an artifact that hijack a downstream LLM.
•Prompt-injection phrasing — instruction-subversion language detected · protectai-llm-guard-168c103/docs/changelog.md (CWE-77)expected
⚠LLM02Sensitive Information Disclosurehigh
Secrets, credentials or PII shipped inside the artifact.
•Embedded credentials — found: GitHub token · protectai-llm-guard-168c103/benchmarks/input_examples.json (CWE-798)expected
•Embedded credentials — found: AWS secret key, GitHub token · protectai-llm-guard-168c103/tests/input_scanners/test_secrets.py (CWE-798)expected
•Low-confidence secret match — possible: JWT · protectai-llm-guard-168c103/tests/input_scanners/test_secrets.py (CWE-798)risk surface
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — destructive rm -rf / · protectai-llm-guard-168c103/.github/workflows/test.yml (CWE-78)expected
•Suspicious code patterns — dynamic code execution · protectai-llm-guard-168c103/llm_guard/output_scanners/factual_consistency.py (CWE-95)expected
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s) · protectai-llm-guard-168c103/.gitignoreexpected
•External endpoints declared — 2 distinct host(s) · protectai-llm-guard-168c103/CONTRIBUTING.mdexpected
•External endpoints declared — 10 distinct host(s) · protectai-llm-guard-168c103/README.mdexpected
•External endpoints declared — 3 distinct host(s) · protectai-llm-guard-168c103/docs/api/deployment.mdexpected
•External endpoints declared — 4 distinct host(s) · protectai-llm-guard-168c103/docs/api/overview.mdexpected
•External endpoints declared — 8 distinct host(s) · protectai-llm-guard-168c103/docs/changelog.mdexpected
•External endpoints declared — 5 distinct host(s) · protectai-llm-guard-168c103/docs/index.mdexpected
•Egress to a private/loopback host — 0.0.0.0 · protectai-llm-guard-168c103/docs/tutorials/litellm.md (CWE-918)expected
•External endpoints declared — 6 distinct host(s) · protectai-llm-guard-168c103/mkdocs.ymlexpected
⚠LLM07System Prompt Leakagehigh
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Embedded credentials — found: GitHub token · protectai-llm-guard-168c103/benchmarks/input_examples.json (CWE-798)expected
•Internal host / private infrastructure reference — shipped content references a private IP range or internal-only host · protectai-llm-guard-168c103/benchmarks/input_examples.json (CWE-200)expected
•Embedded credentials — found: AWS secret key, GitHub token · protectai-llm-guard-168c103/tests/input_scanners/test_secrets.py (CWE-798)expected
•Low-confidence secret match — possible: JWT · protectai-llm-guard-168c103/tests/input_scanners/test_secrets.py (CWE-798)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
◷LLM10Unbounded ConsumptionRuntime-enforced
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
✓LLM03Supply ChainPassed
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
OWASP Machine Learning Security Top 10
⚠ML02Data Poisoninghigh
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
•Prompt-injection phrasing — instruction-subversion language detected · protectai-llm-guard-168c103/docs/changelog.md (CWE-77)expected
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — destructive rm -rf / · protectai-llm-guard-168c103/.github/workflows/test.yml (CWE-78)expected
•Suspicious code patterns — dynamic code execution · protectai-llm-guard-168c103/llm_guard/output_scanners/factual_consistency.py (CWE-95)expected
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓ML06AI Supply ChainPassed
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.
Other findings (5) · hygiene / uncategorized
•Unrecognized file type — '.editorconfig' is not on the allowlist · protectai-llm-guard-168c103/.editorconfigrisk surface
•Unrecognized file type — '.?' is not on the allowlist · protectai-llm-guard-168c103/.github/CODEOWNERSrisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · protectai-llm-guard-168c103/.gitignorerisk surface
•Suspicious network references — raw IP URL (13 URLs) · protectai-llm-guard-168c103/docs/tutorials/litellm.mdexpected
•Malware test signature (EICAR) — EICAR signature present · protectai-llm-guard-168c103/tests/output_scanners/test_ban_substrings.pyexpected
✔ verified source · pinned protectai-llm-guard-168c103
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/llm-guard-input-output-security/check). Click a policy:

Consume LLM Guard — Input/Output Security Toolkit programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/llm-guard-input-output-security

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/llm-guard-input-output-security/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add llm-guard-input-output-security

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/llm-guard-input-output-security/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "llm-guard-input-output-security" })
OpenAPI spec →
vlatest
✓ Security: Safe · 1001mo ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

Free, security-vetted AI capabilities — skills, MCPs, plugins, agents, datasets and more, each graded and freshness-tracked, and built for humans and agents alike.

api · v3.1status · all green
Contact
support@ai-supply.storesecurity@ai-supply.store
Catalog
  • Discover
  • Categories
  • Leaderboards
  • Benchmarks
  • Security
  • Scan a repo
Community
  • Community
  • FAQ
For agents
  • Quickstart (60s)
  • Authorize an agent
  • Agent API
  • OpenAPI spec
For builders
  • Publish
  • Dashboard
Account
  • Create account
  • Sign in
  • Settings
Legal
  • Terms
  • Publisher Agreement
  • Acceptable Use
  • Privacy