eridian-carapace
由 iampaulpatterson-boop 提供
Coding Agents & IDEs简介
Agent security hardening and prompt injection defense for OpenClaw.
描述
该技能的功能
Runtime security hardening for OpenClaw agents. Defends against prompt injection, credential theft, data exfiltration, and unauthorized operations triggered by malicious external content. Provides copy-paste AGENTS.md security patterns, browser URL allowlisting, and approval flows for sensitive operations.
Pre-installation scanners check skills before they run; this hardens the agent itself so malicious instructions embedded in runtime content are caught even if they slip past scanner tools.
何时使用
- Hardening an agent against prompt injection from external web pages or emails
- Preventing credential files like .env and .pem from being read by untrusted sources
- Requiring explicit confirmation before an agent deletes files or modifies configs
- Auditing an existing agent configuration for common attack surface exposures
- Blocking an agent from sending sensitive data to non-allowlisted external URLs
示例工作流
User asks: Harden my OpenClaw agent against prompt injection and credential leaks
- 1
Copies relevant rules from references/security-patterns.md into the project AGENTS.md, placing them near the top
- 2
Creates security/browser-allowlist.json with approved domains
- 3
Reviews references/attack-vectors.md to identify which of the 8 attack vectors apply to the current setup
- 4
Confirms file access restrictions are in place for .env, *.key, openclaw.json, and similar credential files
- 5
Presents a summary of active protections and flags any gaps found via references/audit-template.md
Agent now refuses config modifications from external content, requires explicit owner approval for sensitive operations, and alerts on restricted file access attempts
安装
clawhub install iampaulpatterson-boop/eridian-carapace运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。