Build Landing Page

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by collecting user inputs during a multi-phase interview and directly incorporating them into the generated source code for a Next.js landing page.
  • Ingestion points: User-provided answers to interview questions defined in SKILL.md (e.g., product name, differentiation, and brand voice).
  • Boundary markers: There are no explicit delimiters or instructions to treat user-provided data as potentially untrusted during the generation process.
  • Capability inventory: The skill instructs the agent to generate and deliver complete Next.js, TypeScript, and Tailwind CSS component files.
  • Sanitization: No input validation or sanitization routines are specified for the user-provided content before it is embedded into the source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 02:42 AM
Security Audit — agent-trust-hub — Build Landing Page