skills/jny986/ai-setup/prototype/Gen Agent Trust Hub

prototype

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a legitimate developer tool designed for generating temporary, throwaway code to test logic or UI designs. It does not include any patterns for exfiltration, persistence, or credential theft.- [INDIRECT_PROMPT_INJECTION]: The skill ingests user prompts and project context to generate code artifacts. This represents an attack surface for indirect prompt injection where untrusted data could influence code generation. However, the risk is categorized as low because the generated code is intended for direct developer review and local execution. \n * Ingestion points: User requirements and local project files (SKILL.md).\n * Boundary markers: Not specified in the skill files.\n * Capability inventory: Generates HTML files and React components for manual testing (LOGIC.md, UI.md).\n * Sanitization: Relies on the inherent safety filters of the agent's code generation process.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 10:35 AM