performance
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains legitimate architectural patterns for React and Material UI optimization. It guides the agent on how to implement tree-shaking, bundle analysis, and virtualization using industry-standard libraries.
- [COMMAND_EXECUTION]: The instructions include typical development commands for installing source-map tools and running bundle analysis (e.g.,
npm install --save-dev source-map-explorer,ANALYZE=true npm run build). These operations are restricted to the local development environment. - [INDIRECT_PROMPT_INJECTION]: The skill is scoped to interact with application source code through
allowed-tools(Read, Edit, Write) andglobs(*.tsx, *.ts). This constitutes an indirect prompt injection surface as the agent may process untrusted data within project files. However, no specific malicious payloads or instructions to bypass safety guardrails were identified within the skill's content. - Ingestion points: Reads files matching
*.tsx,*.ts,*.jsx,*.js,webpack.config.*, andnext.config.*(SKILL.md frontmatter). - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: File reading, writing, and editing; shell command execution via Bash (SKILL.md frontmatter).
- Sanitization: None specified for external content processing.
Audit Metadata