Pular para o conteúdo
TakoAPI
Voltar às skills

agentguard

por manas-io-ai

DevOps & Cloud
2.8kDownloads informados pelo clawskills.sh
3Estrelas
0Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

**Category:** Security & Monitoring.

Descrição

O que esta skill faz

Monitors agent file access, outbound API calls, and external communications to detect suspicious behavior. Generates security reports and sends alerts with configurable severity thresholds. All processing runs locally with no external data transmission.

Runs entirely locally with no external data transmission, so sensitive operational data stays on the machine while still providing full audit trails and ML-lite anomaly detection.

Quando usá-la

  • Detecting when an agent reads credential files like .env or API key files
  • Auditing outbound HTTP calls made by a running agent during a session
  • Generating a daily security summary of agent activity and anomalies
  • Investigating file access patterns over a specific time window after a suspected issue
  • Flagging bulk file reads that match data exfiltration patterns

Exemplo de fluxo de trabalho

ENTRADA

User asks: 'What has my agent been doing with files in the last 2 hours?'

AGENTE
  1. 1

    Run agentguard start to confirm monitoring is active

  2. 2

    Run agentguard investigate --timerange 'last 2 hours' --type file_access

  3. 3

    Review returned events grouped by severity level

  4. 4

    Run agentguard alerts --last 24h --severity high to check for flagged incidents

  5. 5

    Run agentguard report --now for a full activity summary

SAÍDA

A breakdown of file access events with severity labels, any triggered alerts, and a list of accessed resource paths from the past two hours

Instalação

clawhub install manas-io-ai/agentguard

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

Links