ui-research
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to browse and analyze external marketplaces and galleries (listed in
references/template-marketplaces.md) to extract layout patterns and design tokens. This creates an attack surface where malicious content on these third-party websites could attempt to influence the agent's behavior via indirect prompt injection. - Ingestion points: External URLs for inspiration galleries and marketplaces defined in the reference files.
- Boundary markers: Absent. The instructions define how to record findings but do not include directives for the agent to ignore instructions potentially embedded in the scraped web content.
- Capability inventory: The skill does not contain executable code itself, but it prepares data for implementation by the
godmode:ui-engineeringskill. - Sanitization: No sanitization or verification process is defined for the content extracted from external URLs.
- [NO_CODE]: The skill consists entirely of Markdown documentation and reference files. It does not include any executable scripts, binaries, or automated installation steps.
Audit Metadata