llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
61
73%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./backend/cli/skills/llm-tools/llamaguard/SKILL.mdLow
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
SKILL.md describes an API endpoint where outsider-supplied text is POSTed to /moderate (FastAPI) as request.messages and then passed into the LLM via tokenizer.apply_chat_template(request.messages, ...), so the required runtime workflow ingests free text directly from users.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill loads the model "meta-llama/LlamaGuard-7b" at runtime (via AutoModel.from_pretrained and vLLM LLM(...) ), which will fetch the model from https://huggingface.co/meta-llama/LlamaGuard-7b and that remote model content directly controls moderation behavior/execution.
- Repository
- synthetic-sciences/openscience
- Commit
52845c3
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.