skills/affaan-m/ecc/angular-developer/Gen Agent Trust Hub

angular-developer

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to operate on local Angular codebases and perform actions such as ng build and ng test. It lacks explicit boundary markers or sanitization for code read from the environment, which could allow instructions embedded in comments or metadata within a project to influence the agent's behavior.
  • [INGESTION_POINTS]: The agent reads codebase files, including components, services, and configurations as part of its primary workflow (SKILL.md).
  • [CAPABILITIES]: The agent has the ability to run build scripts, tests, and package managers (ng, npm, npx).
  • [BOUNDARY_MARKERS]: None identified in the provided instructions.
  • [SANITIZATION]: No explicit sanitization of codebase content is mentioned before processing.
  • [COMMAND_EXECUTION]: The skill explicitly instructs the agent to run terminal commands for project scaffolding (ng new, npx), dependency management (ng add, npm install), and verification (ng build). While these are standard for a developer agent, they involve executing code (via build scripts and tests) which can represent a risk if the codebase is untrusted.
  • [EXTERNAL_DOWNLOADS]: The skill guides the agent to install external dependencies such as @angular/aria, tailwindcss, and various testing frameworks. These downloads target official registries and well-known scopes (@angular, @tailwindcss), making them legitimate developer actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:13 PM
Security Audit — agent-trust-hub — angular-developer