housekeep-design

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Employs the rg (Ripgrep) command-line tool via the shell to scan the repository for hardcoded hex/RGB values, arbitrary Tailwind utility classes, and duplicate component implementations.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted content from repository source files and external unification plans to determine its refactoring actions.
  • Ingestion points: Project source code (TSX, JSX, CSS, Vue) and plan files in .cursor/plans/ used as input for the consolidation process.
  • Boundary markers: The instructions do not specify the use of delimiters or boundary markers when reading and processing code content.
  • Capability inventory: Possesses significant capabilities including repository-wide file modification, shell command execution, and configuration of linting guardrails.
  • Sanitization: No explicit sanitization or validation logic is defined for the content extracted from the codebase before it is used to inform automated edits.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 11:19 AM
Security Audit — agent-trust-hub — housekeep-design