eridian-carapace
Agent security hardening and prompt injection defense for OpenClaw.
Setup & Installation
Install command
clawhub install iampaulpatterson-boop/eridian-carapaceIf the CLI is not installed:
Install command
npx clawhub@latest install iampaulpatterson-boop/eridian-carapaceOr install with OpenClaw CLI:
Install command
openclaw skills install iampaulpatterson-boop/eridian-carapaceor paste the repo link into your assistant's chat
Install command
https://github.com/openclaw/skills/tree/main/skills/iampaulpatterson-boop/eridian-carapaceWhat This Skill Does
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.
When to Use It
- 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
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Hardening an agent against prompt injection from external web pages or emails
- 1Hardening an agent against prompt injection from external web pages or emails
- 2Preventing credential files like .env and .pem from being read by untrusted sources
- 3Requiring explicit confirmation before an agent deletes files or modifies configs
- 4Auditing an existing agent configuration for common attack surface exposures
- 5Blocking an agent from sending sensitive data to non-allowlisted external URLs
Agent security hardening and prompt injection defense for OpenClaw.
Security Audits
These signals reflect official OpenClaw status values. A Suspicious status means the skill should be used with extra caution.