typography-audit

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill is composed of markdown instructions and does not include any executable scripts or libraries.
  • [SAFE]: The skill's workflow is limited to structural UI refactoring and translation key updates within the local project environment.
  • [PROMPT_INJECTION]: The skill processes untrusted code and JSON files, creating an indirect prompt injection surface. 1. Ingestion points: .tsx and .json files. 2. Boundary markers: None present. 3. Capability inventory: Local file modification. 4. Sanitization: None present.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 08:39 PM