llamaguard
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Analysis of the skill instructions and code snippets revealed no malicious patterns. The skill provides integration examples for LlamaGuard moderation using standard, reputable libraries and frameworks.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input for safety classification. It utilizes standard tokenizer chat templates to maintain context boundaries and lacks dangerous execution capabilities (such as shell access or network exfiltration), minimizing the risk associated with processing external content.
Audit Metadata