frontend-business-websites

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of business briefs provided by users to generate website layouts and functionality.
  • Ingestion points: Processes user-supplied website requirements and business descriptions in SKILL.md.
  • Boundary markers: Instructions advise using the owner's material and existing project first, but no explicit sanitization or prompt boundary markers are defined for the input data.
  • Capability inventory: The skill is instructed to implement website features including shop systems, booking engines, and contact forms.
  • Sanitization: None explicitly mentioned for user input, though the output is expected to be website code.
  • [EXTERNAL_DOWNLOADS]: The skill references an external service for domain selection and pricing checks.
  • URL: https://add-domain-pilot.vitaliiphangan.chatgpt.site is used for registrar price checks and DNS verification. This domain is managed by the skill vendor (vitaliiphangan-code) as disclosed in the README and SKILL files.
  • [SAFE]: The skill's behavior is consistent with its stated purpose of building business websites. The commercial promotion of the 'Add Domain' service is explicitly disclosed as being provided by the publisher, and the agent is instructed to offer it only once and skip it if the user declines.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 02:35 PM