improve-codebase-architecture
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches Tailwind CSS and Mermaid.js from well-known CDNs (cdn.tailwindcss.com and cdn.jsdelivr.net) to render the architecture report.- [COMMAND_EXECUTION]: The skill uses platform-specific commands like xdg-open, open, and start to display the generated HTML report to the user.- [PROMPT_INJECTION]: The skill ingests codebase content, domain glossaries, and architecture decision records to generate its analysis, which presents a surface for indirect prompt injection. Ingestion points: Local codebase files, CONTEXT.md, and ADRs. Boundary markers: Absent; the skill does not use specific markers to delimit untrusted codebase content. Capability inventory: Writing to the system temp directory, executing browser-opening commands, and reading arbitrary codebase files. Sanitization: Not specified; codebase content is rendered directly into HTML and Mermaid diagrams.
Audit Metadata