chromatic-monorepo-config
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided repository architecture and configuration data, creating a potential surface for indirect prompt injection.
- Ingestion points: User-supplied descriptions of repository topology, build tools (Nx or Turborepo), and existing configuration files as requested in
template.mdandSKILL.md. - Boundary markers: The instructions do not define clear delimiters or "ignore" markers to isolate user-provided data from the agent's logic, which could allow maliciously crafted repository descriptions to influence the agent's output.
- Capability inventory: The skill generates executable CLI commands (e.g.,
npx nx run) and GitHub Action workflow definitions as seen inreference/snippet-catalog.md. - Sanitization: There are no explicit instructions to sanitize or escape user-provided strings (like package names or file paths) before they are interpolated into the recommended code snippets.
- [EXTERNAL_DOWNLOADS]: The skill recommends the integration of external code for CI/CD workflows.
- Evidence:
reference/snippet-catalog.mdprovides snippets that fetch and executechromaui/action@latest. This resource originates from the skill's author and is a standard component of the recommended service integration.
Audit Metadata