create-lab-guide

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to git clone and read a public GitHub repo (git clone https://github.com/dockersamples/{REPO_NAME}) — including README.md, labspace/labspace.yaml, labspace/*.md and compose.override.yaml — so it ingests and interprets untrusted, user-authored repository content that can change guide generation and runtime decisions (e.g., model-download flag).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill performs a runtime git clone from https://github.com/dockersamples/{REPO_NAME}.git and reads README.md and labspace/*.md to generate the guide, so fetched repository content directly controls the agent's prompts/instructions and is a required dependency.