Skip to main content
SAICA-KG

Tools

llm-guard

2,855

The Security Toolkit for LLM Interactions.

PreventionIn-generationFully autonomousExperimentalTier 3PromptEnvironment
Maturity tier details

Computed tier: 3(raw score 3.88). Effective tier: 3.

Facets:documented_in=0evaluated_on=0integration_surfaces=0.5paper_citations=0recent_commit=2stars=1.38

Source of truth:pipeline/maturity/score.py

Description

ProtectAI's LLM Guard is a runtime security layer for LLM interactions. Pluggable input/output scanners (PII, secrets, prompt injection, jailbreak detection, profanity, toxicity, competitor detection) can be composed as a gate in front of LLM calls, with configurable allow/deny policies.

Why it's included

Canonical runtime-guard toolkit: covers both directions (user→LLM and LLM→user). Differentiated from rebuff by a wider scanner catalogue and from nemo-guardrails by being library-first (no DSL).

Addresses failure modes

  • Security vulnerability — Insecure patterns, injection flaws, weak cryptography, secret leakage.
  • Fabrication — Generating reference to non-existent APIs, packages, or symbols.
  • Scope creep — Actions outside declared task boundary.
  • Context pollution — Trajectory drift, hallucination spirals, overlong or off-task context.

Techniques

input-scannersoutput-scannerspii-detectionprompt-injection-detection

View raw YAML on GitHub →