lwy-requirement-workflow
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The workflow is managed by a bundled Node.js CLI script (scripts/cli.cjs) that handles project state, artifact generation, and phase transitions. It also configures IDE hooks (.trae/hooks.json or .claude/settings.json) that execute shell commands to provide session context and enforce quality gates during session lifecycle events.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Project names and descriptions provided during initialization are interpolated into Markdown 'briefs' (e.g., briefs/DEFINING.md), which are then used as the primary context for AI agent activities in subsequent phases. While the workflow uses markdown headers and blockquotes as boundary markers, it lacks robust sanitization or escaping for user-provided strings before interpolation into agent instructions.
Audit Metadata