better-typography
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and CSS/React code examples for UI development. No executable scripts or binary files are included.
- [SAFE]: No external network requests, data exfiltration patterns, or obfuscation techniques were detected. All URLs are internal references to other markdown files within the skill repository.
- [SAFE]: No attempts at prompt injection, privilege escalation, or persistence mechanisms were found. The instructions focus strictly on typography best practices.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted frontend code for typography issues, representing a data ingestion surface. Ingestion points: Frontend code provided to the agent for review as described in SKILL.md. Boundary markers: None present to distinguish code from instructions. Capability inventory: The skill instructs the agent to write fixes, which may involve file-modification tools. Sanitization: No validation of ingested code is specified. This surface is expected for a code-review utility and is assessed as safe.
Audit Metadata