Skills
skills/agentskillexchange/skills/Filter prompts and model outputs for injection, secrets, toxicity, and policy risks with LLM Guard/Gen Agent Trust Hub

Filter prompts and model outputs for injection, secrets, toxicity, and policy risks with LLM Guard

Pass

Audited by Gen Agent Trust Hub on Jun 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as documentation for a legitimate security tool and does not contain any executable code or malicious instructions.
  • [EXTERNAL_DOWNLOADS]: Recommends installing the llm-guard package from PyPI, which is the standard distribution channel for this library.
  • [EXTERNAL_DOWNLOADS]: Links to official documentation and the source code repository on GitHub belonging to Protect AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 4, 2026, 12:17 PM
Security Audit — agent-trust-hub — Filter prompts and model outputs for injection, secrets, toxicity, and policy risks with LLM Guard