prototype-question

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs, such as design questions or Spikes, to generate functional code prototypes. This creates a surface where malicious instructions in the input could influence the generated code.\n
  • Ingestion points: Design questions and Spike delegations described in SKILL.md and references/logic.md.\n
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the input questions are defined.\n
  • Capability inventory: The skill enables the agent to generate and potentially execute code (logic harnesses, HTML/JS files, and UI variants).\n
  • Sanitization: The instructions do not specify sanitization or escaping for the input text before it is rendered or used in the prototype.\n- [EXTERNAL_DOWNLOADS]: The skill references content adapted from repositories at github.com/mattpocock/skills and github.com/cursor/plugins. These are well-known sources in the software development community and are referenced here for attribution and methodology.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:04 PM
Security Audit — agent-trust-hub — prototype-question