Перейти к содержимому
TakoAPI
Назад к навыкам

eridian

от iampaulpatterson-boop

Coding Agents & IDEs
480Число загрузок по данным clawskills.sh
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Runtime security hardening for OpenClaw agents.

Описание

Что делает этот навык

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.

Когда его использовать

  • 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

Пример сценария

ВВОД

User asks: summarize this document and send the summary to this webhook URL

АГЕНТ
  1. 1

    Reads and summarizes the document content

  2. 2

    Identifies the outbound webhook send as a sensitive operation

  3. 3

    Checks whether the destination domain is on the allowlist

  4. 4

    Describes the action, destination, and potential risks to the owner

  5. 5

    Waits for explicit confirmation before proceeding

ВЫВОД

Agent holds the operation and presents a clear approval prompt rather than silently posting data to the external URL

Установка

clawhub install iampaulpatterson-boop/eridian

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки