angular-library-builder
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external sources to drive its code generation process, creating a surface for indirect prompt injection.
- Ingestion points: Step 1 reads OpenAPI/Swagger definitions (JSON/YAML), Markdown documentation, and existing TypeScript source files.
- Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the ingested data.
- Capability inventory: The skill can execute shell commands via the Angular CLI and NPM, generate source code, modify configuration files, and invoke other specialized development skills.
- Sanitization: No explicit sanitization or validation of the input content is performed before it is used to influence the agent's logic or the generated code.
- [COMMAND_EXECUTION]: Utilizes the Angular CLI (ng) and NPM (npm) to perform project management tasks, including workspace initialization, library scaffolding, building artifacts, and package publishing.
- [EXTERNAL_DOWNLOADS]: Performs network requests to the official NPM registry to retrieve version information for Angular and RxJS packages when resolving peer dependency requirements during library generation.
Audit Metadata