nestjs-expert
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard shell utilities such as 'grep', 'find', and 'test' for project diagnostics. It also executes framework-specific commands including 'nest info' and project scripts such as 'npm run build' and 'npm run test' to validate fixes. These actions are within the expected scope of a framework expert.
- [EXTERNAL_DOWNLOADS]: The skill references standard Nest.js ecosystem packages (e.g., @nestjs/core, @nestjs/passport) and links to official documentation at docs.nestjs.com. All external references target trusted domains and well-known services.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted project data and has the capability to execute commands.
- Ingestion points: Reads project configuration files (package.json, nest-cli.json, tsconfig.json) and source code (src/**/*.ts).
- Boundary markers: No explicit delimiters are used to separate ingested project content from agent instructions.
- Capability inventory: Can execute arbitrary code via 'npm run test' or 'npm run build' if these scripts are modified in the project's package.json.
- Sanitization: No sanitization or validation of ingested file content is mentioned before processing or execution.
Audit Metadata