IronClaw Agent Guard

- Do not claim full containment or malware protection.

Community View Source →

LLM Evaluation

Evaluated by: xiaomi/mimo-v2-flash:free

Last evaluated: April 05, 2026

Prompt Quality

3.0 /5

Evaluation error: RetryError[]

Usefulness

3.0 /5

Evaluation error: RetryError[]

Overall Rating

3.0 /5

Evaluation failed

Prompt Preview

---
name: ironclaw-agent-guard
description: Use this skill when reviewing proposed tool calls, shell commands, outbound requests, or agent messages for destructive actions, prompt injection, secret leaks, or sensitive path exposure before execution.
homepage: https://github.com/wd041216-bit/ironclaw-agent-guard
---

# IronClaw Agent Guard

Use this skill when an agent workflow is about to:

- run shell commands that might be destructive
- send messages or HTTP requests that might leak secrets
-...

Full prompt length: 1784 characters