Skills
Navigate
skills/rebyteai-template/rebyte-skills/kubecon-llm-k8s/Gen Agent Trust Hub

kubecon-llm-k8s

Warn

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to clone a repository from https://github.com/Eng0AI/kubecon-llm-k8s-template.git. This source is not verified.
  • [REMOTE_CODE_EXECUTION]: The skill executes pnpm install and pnpm build on the contents of the externally cloned repository. This allows for the execution of arbitrary code via Node.js lifecycle scripts (such as preinstall or postinstall) defined in the downloaded package.json file.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external repository which could influence subsequent agent actions.
  • Ingestion points: All files within the cloned repository kubecon-llm-k8s-template.
  • Boundary markers: None present.
  • Capability inventory: Shell command execution via git, pnpm, vercel, and netlify.
  • Sanitization: None present.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 23, 2026, 06:06 PM