Skip to main content

llamaguard

LlamaGuard provides advanced content moderation for LLMs, ensuring safe interactions by filtering harmful inputs and outputs with high accuracy.

Install this skill

or
89/100

Security score

The llamaguard skill was audited on Feb 28, 2026 and we found 7 security issues across 2 threat categories. Review the findings below before installing.

Categories Tested

Security Issues

medium line 183

Curl to non-GitHub URL

SourceSKILL.md
183curl -X POST http://localhost:8000/moderate \
low line 183

External URL reference

SourceSKILL.md
183curl -X POST http://localhost:8000/moderate \
low line 257

External URL reference

SourceSKILL.md
257https://huggingface.co/meta-llama/LlamaGuard-7b
low line 329

External URL reference

SourceSKILL.md
329- V1: https://huggingface.co/meta-llama/LlamaGuard-7b
low line 330

External URL reference

SourceSKILL.md
330- V2: https://huggingface.co/meta-llama/Meta-Llama-Guard-2-8B
low line 331

External URL reference

SourceSKILL.md
331- V3: https://huggingface.co/meta-llama/Meta-Llama-Guard-3-8B
low line 332

External URL reference

SourceSKILL.md
332- Paper: https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/
Scanned on Feb 28, 2026
View Security Dashboard
Installation guide →