better-typography
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project source code, such as CSS, Tailwind utility classes, and HTML/JSX components, to identify typography issues and applies fixes to the project's styling system. This ingestion of untrusted data, combined with the capability to write modifications to the project, creates an attack surface where malicious instructions embedded in the code or comments could potentially influence the agent's behavior.
- Ingestion points: Project styling files, including CSS stylesheets and React/HTML components (referenced in SKILL.md and details-and-accessibility.md).
- Boundary markers: No specific delimiters or safety instructions are provided to help the agent distinguish between data to be analyzed and embedded instructions.
- Capability inventory: The skill is designed to write fixes back to the project's styling system, which involves file modification capabilities.
- Sanitization: The instructions do not specify any validation, escaping, or filtering of the ingested styling content before processing or modification.
Audit Metadata