lov-refactor-modular

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes Python scripts (scripts/profile_store.py and scripts/validate_skill.py) that perform local filesystem operations for configuration management and source code validation.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external source code files for refactoring, which constitutes a potential attack surface. * Ingestion points: The skill reads target files and project context as specified in the workflow instructions. * Boundary markers: The skill relies on natural language instructions for refactoring steps without implementing explicit boundary markers for the ingested code. * Capability inventory: The skill employs file system read/write capabilities and local script execution to fulfill its purpose. * Sanitization: There is no evidence of explicit content sanitization for the ingested code before processing.
  • [EXTERNAL_DOWNLOADS]: The skill references external dependencies and installation tools. * Dependencies: The validate_skill.py script requires the PyYAML package from a standard registry. * Installation: The README recommends installation via npx, a standard node package runner.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 09:49 AM
Security Audit — agent-trust-hub — lov-refactor-modular