← Browse
agentguards-claude
alelaguard ★ 4
This plugin enforces LLM security guardrails on Claude Code through hooks that scan prompts for jailbreak/injection attacks, authorize Bash commands, block data exfiltration, and redact web-fetched content before the model sees it. All enforcement is fail-closed by default and backed by the AgentGuards REST API for detection and blocking of risky inputs and outputs.
Install
> /plugin marketplace add alelaguard/agentguards-plugins/tree/HEAD/claude
> /plugin install agentguards-claude
Source: https://github.com/alelaguard/agentguards-plugins/tree/HEAD/claude
What it's made of
3 skills · 3 hooks
- Commands
- 0
- Agents
- 0
- Skills
- 3
- MCP servers
- 0
- Hooks
- 3 · PostToolUse, PreToolUse, UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- AgentGuards
- External tools
run-hook.sh- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (alelaguard).