Agent Hardening
@clawhub_zurbrick/agent-hardening-zurbrick
By zurbrick
About this Skill
Lock down any LLM agent against prompt injection, data exfiltration, social engineering, and channel-based attacks. Use when setting up a new agent, auditing...
安全扫描故障排查
Skill files and instructions
Read SKILL.md and the other instructions or configuration files published with this Skill.
Loading file list
Details
- Category
- IT Ops & Security
- Source
- clawhub
- Version
- 1.1.0
- Updated
- Sep 24, 2026