Lewati ke konten
TakoAPI
Kembali ke skill

aegis-shield

oleh deegerwalker

Web & Frontend Development
688Unduhan dilaporkan oleh clawskills.sh
0Tayangan
0 sukaMasuk untuk menyukai skill ini
—Belum ada penilaian
Penilaian Anda

Ringkasan

Prompt-injection and data-exfiltration screening for untrusted text.

Deskripsi

Apa yang Dilakukan Skill Ini

Screens untrusted text for prompt injection, data exfiltration, and tool-abuse patterns before it reaches memory or other tools. Assigns a severity score and routes content to either acceptance or quarantine. Includes a safe memory append workflow that enforces scan and lint checks before any write.

Intercepts malicious content at the boundary rather than relying on downstream tools to handle hostile input safely.

Kapan Menggunakannya

  • Scanning email content before summarizing it to an agent
  • Screening scraped web pages before feeding them into a pipeline
  • Quarantining social media replies that contain suspicious instructions
  • Enforcing sanitized memory writes when processing user-supplied input
  • Blocking exfiltration attempts hidden in LLM-targeted document payloads

Contoh Alur Kerja

INPUT

User asks: scan this webpage content before summarizing it

AGENT
  1. 1

    Pass the raw fetched text to the scan step

  2. 2

    Receive severity score and flag list from the scanner

  3. 3

    Check if severity is medium or higher

  4. 4

    If severity is medium+, route content to quarantine and halt pipeline

  5. 5

    If severity is low, proceed to summarize the sanitized text

OUTPUT

Content is either quarantined with a report or cleared for downstream use

Instalasi

clawhub install deegerwalker/aegis-shield

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

Tautan