frontend-design

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a 'client's design brief' to generate frontend code, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: The skill instructions in SKILL.md specify that the agent should confirm and use the 'client's design brief' and any 'information in your memory about the client's preferences' as the primary input for its design process.\n
  • Boundary markers: There are no defined delimiters or instructions to ignore embedded commands within the ingested brief or context data.\n
  • Capability inventory: The skill involves writing executable frontend code (HTML, CSS, JS) and mentions the use of screenshot tools for visual critique (SKILL.md).\n
  • Sanitization: The instructions do not include steps for sanitizing, escaping, or validating the content of the external brief before it is used to generate code.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 01:50 PM