deep-research

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell commands via pnpm to synchronize research artifacts with a local blog repository. This behavior is a documented feature of the lovstudio research-to-publishing pipeline.
  • [EXTERNAL_DOWNLOADS]: Documentation recommends the installation of third-party tools such as search-cli for multi-provider search and weasyprint for PDF generation to enable the skill's full feature set.
  • [COMMAND_EXECUTION]: Internal test suites (e.g., test_citation_manager.py, test_evidence_store.py) utilize subprocess calls to verify the command-line interface and functionality of the provided Python scripts.
  • [COMMAND_EXECUTION]: The methodology instructions guide the agent to use shell commands like date and search-cli to perform real-time information retrieval and ensure temporal accuracy.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 03:53 PM
Security Audit — agent-trust-hub — deep-research