audit-frontend-design
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
npxto run a diagnostic tool on the local filesystem. - Evidence: Commands
npx -y @memi-design/cli@2.7.9 diagnose .,ux audit, andcraft auditinSKILL.md. - [EXTERNAL_DOWNLOADS]: The skill uses
npxto download and run the@memi-design/clipackage from the npm registry. - Evidence:
npx -y @memi-design/cli@2.7.9inSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code from a local repository, which could contain instructions intended to influence the agent's audit findings or subsequent code edits.
- Ingestion points: The local repository files (indicated by the
.path) processed by the audit commands inSKILL.md. - Boundary markers: Absent. No specific delimiters or instructions are provided to the agent to disregard instructions embedded within the source files.
- Capability inventory: The skill can execute shell commands (
npx) and suggests implementing code fixes based on audit output. - Sanitization: Absent. There is no evidence of filtering or sanitizing the content of the repository files before processing.
Audit Metadata