improve-codebase-architecture

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git log to identify codebase hot spots and utilizes platform-specific commands like open, xdg-open, and start to display the generated architectural reports.\n- [EXTERNAL_DOWNLOADS]: The skill incorporates libraries from well-known services, specifically fetching the Tailwind CSS framework from cdn.tailwindcss.com and the Mermaid.js library from cdn.jsdelivr.net.\n- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection as it processes untrusted codebase data without explicit sanitization.\n
  • Ingestion points: commit history (git log), CONTEXT.md, docs/adr/, and general repository content.\n
  • Boundary markers: No delimiters or isolation instructions are present to separate external content from agent instructions.\n
  • Capability inventory: The agent can execute shell commands (git, open) and write to the system's temporary directory.\n
  • Sanitization: There is no evidence of validation or escaping of codebase content before it is interpolated into prompts or the HTML report; additionally, the Mermaid diagram component is configured with securityLevel: "loose", which could allow the execution of injected scripts within diagrams.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 01:21 AM
Security Audit — agent-trust-hub — improve-codebase-architecture