yc-web-design-strategy

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection when analyzing external website content during design audits.
  • Ingestion Points: External website URLs and content provided by users for review, critique, or audit (as triggered by instructions in SKILL.md).
  • Boundary Markers: Absent; there are no instructions to the agent to distinguish between its own guidelines and potential instructions embedded in the audited data.
  • Capability Inventory: The agent is directed to write hero copy, plan page architecture, and use the frontend-design skill for visual execution based on its findings.
  • Sanitization: No sanitization, validation, or escaping of external content is prescribed.
  • [NO_CODE]: The skill consists exclusively of markdown documentation and reference checklists; no executable scripts, binaries, or active code components are included.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 07:03 PM