# AgentGuard

> Protect AI agents by detecting and blocking prompt, command injection, Unicode bypass, and social engineering attacks with customizable security controls.

- **URL**: https://www.freshcrate.ai/projects/AgentGuard
- **Author**: astecka-m
- **Category**: MCP Servers
- **Latest version**: `main@2026-06-05` (2026-06-05)
- **License**: Unknown
- **Source**: https://github.com/astecka-m/AgentGuard
- **Language**: Python
- **GitHub**: 1 stars
- **Registry**: github
- **Tags**: `ai`, `ai-agents`, `ai-governance`, `ai-regulation`, `ai-safety`, `anthropic-claude`, `claude`, `debugging`, `mcp`, `python`

## Description

Protect AI agents by detecting and blocking prompt, command injection, Unicode bypass, and social engineering attacks with customizable security controls.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `main@2026-06-05` | 2026-06-05 | High | Latest activity on main branch |
| `0.0.0` | 2026-04-11 | High | No release found — using repo HEAD |

## Dependency audit

- **Score**: 81/100
- **Total deps**: 3
- **Resolved**: 1
- **Unresolved**: 2
- **License conflicts**: 0
- **Warnings**: 3
- **Scanned**: 2026-04-27

## Citation

- HTML: https://www.freshcrate.ai/projects/AgentGuard
- Markdown: https://www.freshcrate.ai/projects/AgentGuard.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/AgentGuard/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._