landing-page-design
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional text and design tokens (Tailwind classes, hex colors, and spacing values) intended for generating user interface code. No dangerous commands, obfuscation, or unauthorized network operations were found.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection because it is designed to review and redesign existing web content which may contain untrusted data.
- Ingestion points: The skill instructs the agent to review, build, and edit marketing sites, components, and prototypes based on user-provided project data (SKILL.md).
- Boundary markers: Absent. The instructions do not provide specific delimiters or guidance to ignore instructions embedded in the data being reviewed.
- Capability inventory: The skill's capabilities are restricted to generating and modifying front-end code (HTML, CSS, JS) and marketing copy; it does not utilize tools for file system modification, network exfiltration, or arbitrary command execution (SKILL.md).
- Sanitization: Absent. The skill does not provide methods for sanitizing or escaping content retrieved from external project files or sites.
Audit Metadata