prototype
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional markdown files that guide an AI agent in software engineering tasks. It does not contain executable code, remote script downloads, or credential harvesting patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process where the agent interprets user prompts to generate application logic and UI components, which is a standard but noteworthy attack surface for AI agents. Ingestion points: The agent is instructed to use the 'user's prompt' and 'surrounding code' as the primary input for determining prototype requirements in SKILL.md. Boundary markers: The instructions do not specify delimiters or safety instructions to isolate user-provided requirements from the agent's logic. Capability inventory: The agent is empowered to write new files, modify existing routes, and perform git operations such as committing code to project branches (SKILL.md, UI.md). Sanitization: The skill does not describe specific sanitization or validation steps for user-provided design inputs.
Audit Metadata