code-generation-template
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of documentation and code examples for building code generators. It uses standard libraries for template processing and file system operations consistent with its stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for ingesting external data (e.g., OpenAPI specs, CLI inputs) to generate code. This defines a surface where untrusted input could potentially influence the generated output.
- Ingestion points:
references/openapi-client-generation.md(OpenAPI spec parsing) andreferences/project-scaffolding.md(CLI user prompts). - Boundary markers: Not explicitly implemented in the provided templates.
- Capability inventory: File system writes (
fs.writeFile,fs.ensureDir) and directory management across multiple reference scripts. - Sanitization: Includes helpers for naming conventions (pascalCase, kebabCase) but lacks general input validation or escaping for the generated content.
Audit Metadata