create-lab-guide
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- External Repository Ingestion: The skill clones repositories from the dockersamples organization on GitHub to retrieve source material for documentation. This is a standard operation for documentation automation using vendor-provided templates.
- Automated Command Execution: The skill uses git for cloning, npx for formatting with the rumdl package, and docker buildx for linting. These tools are used within the scope of documentation generation and validation.
- Indirect Prompt Injection Surface: The skill processes external data to generate guide content, which is a potential surface for indirect instructions. 1. Ingestion points: README.md and labspace.yaml (SKILL.md). 2. Boundary markers: None identified. 3. Capability inventory: git clone, npx, docker buildx, and file writing (SKILL.md). 4. Sanitization: None identified. The risk is minimized as the skill targets vendor-owned repositories.
Audit Metadata