Lewati ke konten
TakoAPI
Kembali ke skill

eridian

oleh iampaulpatterson-boop

Coding Agents & IDEs
480Unduhan dilaporkan oleh clawskills.sh
0Tayangan
0 sukaMasuk untuk menyukai skill ini
—Belum ada penilaian
Penilaian Anda

Ringkasan

Runtime security hardening for OpenClaw agents.

Deskripsi

Apa yang Dilakukan Skill Ini

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.

Kapan Menggunakannya

  • 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

Contoh Alur Kerja

INPUT

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

AGENT
  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

OUTPUT

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

Instalasi

clawhub install iampaulpatterson-boop/eridian

Jalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.

Tautan