Pular para o conteúdo
TakoAPI
Voltar às skills

aegis-shield

por deegerwalker

Web & Frontend Development
688Downloads informados pelo clawskills.sh
0Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

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

Descrição

O que esta skill faz

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.

Quando usá-la

  • 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

Exemplo de fluxo de trabalho

ENTRADA

User asks: scan this webpage content before summarizing it

AGENTE
  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

SAÍDA

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

Instalação

clawhub install deegerwalker/aegis-shield

Execute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.

Links