improve-codebase-architecture

Warn

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git log to analyze codebase history and uses system-specific commands (open, xdg-open, start) to display the generated HTML report to the user.- [EXTERNAL_DOWNLOADS]: The generated architectural report fetches the Tailwind CSS library and the Mermaid diagramming library from well-known content delivery networks (tailwindcss.com and jsdelivr.net).- [DYNAMIC_EXECUTION]: The skill configures the Mermaid library with securityLevel: "loose" in the generated HTML report. This setting allows HTML tags to be rendered within diagrams, which presents a cross-site scripting (XSS) risk if untrusted data from the codebase is included in the visuals without proper sanitization.- [INDIRECT_PROMPT_INJECTION]:\n
  • Ingestion points: The skill reads source code files, commit history, and architectural documentation (CONTEXT.md, ADRs).\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided when processing project files.\n
  • Capability inventory: The skill can write files to the system temporary directory, spawn sub-agents, and execute shell commands to open the generated files.\n
  • Sanitization: The instructions do not specify any escaping or sanitization of codebase content before it is written into the HTML report.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 1, 2026, 02:01 PM
Security Audit — agent-trust-hub — improve-codebase-architecture