better-layout
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed entirely of markdown documentation and configuration metadata. There are no scripts, binaries, or automated tasks, which eliminates the possibility of direct execution attacks.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a code reviewer, requiring it to process external project styling and structure. This creates a surface for indirect prompt injection where malicious code could attempt to influence the agent. However, given the skill's limited capabilities (textual reporting only), this risk is low and inherent to its purpose.
- Ingestion points: Project CSS styles, HTML DOM structure, and styling tokens (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands in the analyzed code.
- Capability inventory: The skill is restricted to generating textual reports based on layout principles. It has no tool access, file-writing permissions, or network capabilities.
- Sanitization: There are no described mechanisms for filtering or sanitizing the data ingested from the project.
Audit Metadata