open-design-landing
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data (brand briefs) and interpolates it directly into the generated HTML files without sanitization. This allows malicious instructions or scripts embedded in the brief to persist in the resulting marketing site (XSS).
- Ingestion points: Untrusted brand data enters via
inputs.json, which is populated by the agent based on user responses. - Boundary markers: No delimiters or safety instructions are used to wrap the interpolated data in the generation logic.
- Capability inventory: The skill possesses
file-writecapabilities to generate the artifact andnode-runtimeto execute the transformation scripts. - Sanitization: The
scripts/compose.tsfile directly interpolates fields likebrand.name,hero.lead, andMixedTextsegments into the HTML string without escaping or sanitizing HTML entities.
Audit Metadata