tailwind-class-optimizer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE] (SAFE): The provided skill contains only a markdown definition file (SKILL.md) and no executable scripts or logic components.
- [PROMPT_INJECTION] (LOW): The skill defines a surface for Indirect Prompt Injection (Category 8). It is designed to ingest and process untrusted frontend code (React, Vue, CSS) and has access to high-privilege tools including 'Bash', 'Write', and 'Edit'.
- Ingestion points: User-provided frontend code snippets (HTML/JS/CSS).
- Boundary markers: None defined in the metadata to prevent the agent from obeying instructions hidden in user code.
- Capability inventory: Includes 'Bash', 'Write', and 'Edit', which could be abused if the agent is misled by malicious data.
- Sanitization: None specified.
Audit Metadata