digital-brain

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes local automation scripts in the agents/scripts/ directory, such as weekly_review.py and content_ideas.py. These scripts are designed to process local data files within the skill's environment and do not perform network operations or access sensitive system paths.
  • [SAFE]: The installation script scripts/install.sh facilitates local setup by copying skill files to the appropriate directory (e.g., ~/.claude/skills/). It operates with user interaction and follows standard, transparent installation procedures.
  • [INDIRECT_PROMPT_INJECTION]: The skill manages and processes user-populated data from JSONL files (e.g., contacts.jsonl, bookmarks.jsonl). While this represents an ingestion surface for external data, the system relies on structured schemas and does not execute untrusted code derived from these inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:42 PM
Security Audit — agent-trust-hub — digital-brain