skills/steveclarke/dotfiles/architect/Gen Agent Trust Hub

architect

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled script scripts/architect.sh to handle configuration and state management.
  • [COMMAND_EXECUTION]: The skill uses Git commands (add, commit, push) to persist assessment findings in the user's repository as markdown files.
  • [PROMPT_INJECTION]: The skill has an inherent surface for indirect prompt injection (Category 8) because it reads and analyzes content from the user's codebase. Findings: 1. Ingestion points: Codebase files read during analysis phases. 2. Boundary markers: The skill uses structured prompts for sub-agents to focus analysis on architectural patterns. 3. Capability inventory: Local script execution and Git operations. 4. Sanitization: Relies on LLM reasoning and structured JSON output to process and report on codebase content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 12:52 PM