nx-workspace-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates generating files and executing workspace commands through the Nx CLI using user-supplied parameters such as project names, scopes, and directory structures. This creates a surface where malicious input could potentially influence agent actions or file system operations.
- Ingestion points: Variable inputs such as 'name', 'scope', and 'directory' used in custom generators (SKILL.md, Template 4) and command templates.
- Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within user-provided strings used for project configuration.
- Capability inventory: File system write access via generator utilities ('generateFiles', 'formatFiles') and shell command execution capabilities via the Nx CLI ('nx affected', 'nx g', 'nx migrate').
- Sanitization: No explicit sanitization, validation, or path-traversal checks are included for the user-provided 'name' or 'directory' strings before they are interpolated into file paths and command arguments.
Audit Metadata