eridian
bởi iampaulpatterson-boop
Coding Agents & IDEsTóm tắt
Runtime security hardening for OpenClaw agents.
Mô tả
Kỹ năng này làm gì
Runtime security hardening for OpenClaw agents. Guards against prompt injection from external content, credential file exfiltration, and unauthorized operations. Works alongside pre-installation skill scanners by enforcing security rules during execution.
Pre-installation scanners catch known-bad skills before they run, but carapace enforces behavioral rules at runtime, stopping attacks that only materialize during execution.
Khi nào nên dùng
- Blocking hidden instructions in scraped web pages from hijacking agent behavior
- Preventing malicious skill content from reading .env or credential files
- Requiring explicit confirmation before the agent sends data to external endpoints
- Restricting browser navigation to an approved domain allowlist
- Running a structured security audit against an agent's current configuration
Quy trình ví dụ
User asks: summarize this document and send the summary to this webhook URL
- 1
Reads and summarizes the document content
- 2
Identifies the outbound webhook send as a sensitive operation
- 3
Checks whether the destination domain is on the allowlist
- 4
Describes the action, destination, and potential risks to the owner
- 5
Waits for explicit confirmation before proceeding
Agent holds the operation and presents a clear approval prompt rather than silently posting data to the external URL
Cài đặt
clawhub install iampaulpatterson-boop/eridianChạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.