better-typography

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: Analysis of the skill instructions and reference documents found no evidence of malicious patterns, obfuscation, or unauthorized data access. The skill content consists of design principles and CSS references.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a surface for processing user-provided code, but it lacks the necessary capabilities to be exploited maliciously.
  • Ingestion points: Frontend code (CSS, JSX, TSX) and text content provided for typographic review (SKILL.md).
  • Boundary markers: None explicitly defined to delimit user data from agent instructions.
  • Capability inventory: The skill includes no scripts or tool-use permissions for file writing, command execution, or network access.
  • Sanitization: No sanitization or escaping is performed on ingested content.
  • [NO_CODE]: The skill does not include any scripts, binary executables, or package dependency files, significantly reducing the attack surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 01:38 PM
Security Audit — agent-trust-hub — better-typography