Task
SkillSecurityReviews AI agent architectures (API gateways, WAFs, input sanitization) for prompt injection risks.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Task skill
What this skill tells your AI
The instructions your AI receives, as published by gke-labs/kube-agents in .agents/skills/review-security-k8s-agents-prompt-injection/SKILL.md and read by ahel’s review.
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/EnvVarscannot be tampered with by less privileged workloads.
Signals
- GitHub stars
- 54
- Forks
- 36
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
review-security-k8s-agents-prompt-injection- Source
- github.com/gke-labs/kube-agents