Responsive Layout Reviewer

Warn

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Metadata inconsistency: The author name specified in the skill metadata ('simplyutils') does not match the system-reported author ('notysoty').
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified due to the ingestion of untrusted code snippets for review without sufficient security boundaries.
  • Ingestion points: Processes user-supplied HTML, CSS, and React component code as part of the review task described in SKILL.md.
  • Boundary markers: Absent; instructions do not include delimiters or specific guidance to ignore instructions embedded in code data.
  • Capability inventory: The skill provides textual analysis and reporting but does not define or require the use of dangerous tools or network operations.
  • Sanitization: No validation or sanitization is applied to the code being reviewed.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 29, 2026, 05:57 AM
Security Audit — agent-trust-hub — Responsive Layout Reviewer