audit-frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
npxto download and execute the@memi-design/clipackage. This is a vendor-owned resource associated with the skill author, using a pinned version (2.7.9) which is a standard development practice. - [COMMAND_EXECUTION]: Shell commands are used to initiate design audits on the repository's source code. The commands include the
--no-writeflag, which restricts the tool from making unauthorized modifications to the filesystem during the diagnostic phase. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes and audits the content of the repository's source tree.
- Ingestion points: Local source files (React, Next.js) analyzed by the diagnostic tool in
SKILL.md. - Boundary markers: Not present; the agent treats the tool's output as evidence-backed findings.
- Capability inventory: Executes a CLI tool via
npxto read and analyze file structures. - Sanitization: None detected; the agent is instructed to group and report findings based on the tool's output.
Audit Metadata