taste-design-review

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external interfaces (landing pages, SaaS apps, and portfolios) during the audit process.
  • Ingestion points: Data enters the context through the capture and review of external interface screenshots and associated metadata described in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the audited interfaces.
  • Capability inventory: The skill instructions include a phase to 'fix' findings in ranked order, which involves code modification capabilities across the project scripts.
  • Sanitization: There are no explicit sanitization or validation steps mentioned for data retrieved from the external interfaces being audited.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 06:06 AM
Security Audit — agent-trust-hub — taste-design-review