End To End App Development
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill architecture processes user-provided application goals and requirements to drive automated tasks like project scaffolding and dependency installation. This creates a standard surface where malicious user-provided instructions could attempt to influence downstream agent actions.
- Ingestion points: User-defined problem statements, personas, and requirements captured in Phase 1 (Ideation) and Phase 2 (PRD).
- Boundary markers: The skill relies on its 8-phase sequential structure but does not define explicit delimiters to isolate user-provided data from system instructions.
- Capability inventory: The skill executes shell commands for project scaffolding (
npx create-vite) and package management (npm install) during Phases 5 and 6. - Sanitization: The skill includes a dedicated 'Security Audit' in Phase 8 to check for exposed API keys and common web vulnerabilities like XSS and SQL injection.
Audit Metadata