skills/howells/arc/build/Gen Agent Trust Hub

build

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs several shell-based operations to manage the development lifecycle.
  • It uses git for branch management, worktree creation, and committing changes.
  • It executes build and test tools via pnpm, specifically vitest, tsc, and biome.
  • It utilizes a specialized tool (mcp__claude-in-chrome__computer) to capture screenshots for UI verification.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface where untrusted project data could influence behavior.
  • Ingestion points: Rules are loaded from .ruler/*.md and rules/interface/*.md.
  • Boundary markers: The skill uses a structured 'Build Plan' and user confirmation steps (AskUserQuestion).
  • Capability inventory: Sub-agents have permissions to read/write files, manage git, and execute commands.
  • Sanitization: No explicit sanitization of ingested rule files is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 09:27 AM