Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

Loslegen

review-security-k8s-agents-prompt-injection

Sterne36

Forks26

Aktualisiert21. Mai 2026 um 19:48

Reviews AI agent architectures (API gateways, WAFs, input sanitization) for prompt injection risks.

Installation

Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.

In Manus ausführen

Quelle

gke-labs

gke-labs/kube-agents

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

In Manus ausführen

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

InformationssicherheitsanalystenInformatik- und Mathematikberufe·SOC 15-1212

SKILL.md

readonly

name	review-security-k8s-agents-prompt-injection
description	Reviews AI agent architectures (API gateways, WAFs, input sanitization) for prompt injection risks.

Task

Review configurations, API gateways, and input architectures for prompt injection and malicious payload vulnerabilities.

Checks

1. Input Sanitization & Proxies

Gateway/WAF: Require LLM-specific API Gateway or WAF sidecar. Flag raw agent APIs exposed to untrusted traffic.
Guardrails: Ensure system prompts/safety instructions in ConfigMaps/EnvVars cannot be tampered with by less privileged workloads.

Mehr aus diesem Repository

gleiches Repository

github-issue-resolver

gke-labs/kube-agents

Autonomously poll, triage, investigate, and resolve unaddressed open issues on our target GitHub repository strictly within authorized scope.

2026-07-1536

gke-compute-classes

gke-labs/kube-agents

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto Provisioning configuration or general GKE cluster creation.

2026-07-1436

kube-agents-observability

gke-labs/kube-agents

Audit, monitor, and debug the logging, tracing, metrics, and API/dashboard observability of the Platform Agent.

2026-07-1436

gke-manifest-generation

gke-labs/kube-agents

Standard Operating Procedure (SOP) for generating and updating secure, compliant, and cost-effective GKE manifests.

2026-07-1036

gke-workload-troubleshooting

gke-labs/kube-agents

Systematic Standard Operating Procedure (SOP) for diagnosing GKE workload failures, crash loops, resource OOMs, mounting errors, and connectivity timeouts.

2026-07-1036

review-security-k8s-pod

gke-labs/kube-agents

Reviews Kubernetes Pod security contexts for workload-level isolation and privilege escalation risks.

2026-06-1636

Jeden Skill mit einem Klick ausführen