dot-ui-angular-standards
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
pnpmandnxfor standard development tasks such as installing dependencies, serving the UI, running tests, and building the project. These are standard commands for a Node.js/Nx monorepo environment. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and modify frontend source code (TypeScript, HTML, SCSS) and configuration files, which presents a surface where malicious instructions embedded in project files could be ingested by the agent.
- Ingestion points: Reads component files, services, templates, and workspace configurations (
package.json,nx.json) in thecore-web/directory. - Boundary markers: None present; the skill assumes a trusted project environment.
- Capability inventory: The agent is authorized to modify files and execute shell commands (
pnpm nx). - Sanitization: No specific sanitization or filtering of external code content is defined within the skill.
- [SAFE]: The skill uses local relative paths for documentation and references vendor-appropriate resources (
dotcms). The prompt override mechanism is used legitimately to scope coding standards within a specific project directory.
Audit Metadata