im-local-kb

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a logical local knowledge management system using a structured directory hierarchy (kb/00 to kb/04). It provides utility scripts for common maintenance tasks like backups and structure validation.
  • [SAFE]: No signs of prompt injection or attempts to override safety filters were found in SKILL.md or the sub-agent definition. The instructions are focused on structured data extraction and logical reasoning.
  • [SAFE]: The Python scripts (SCRIPT_normalize_merge.py, SCRIPT_extract_knowledge.py, etc.) perform legitimate file I/O operations (reading chat logs, writing structured Markdown, creating ZIP backups) using standard libraries like os, pathlib, re, and zipfile. There are no hidden network calls, obfuscated payloads, or commands that attempt to access sensitive system files (e.g., SSH keys or cloud credentials).
  • [SAFE]: The use of a sub-agent (im-local-db_knowledge-extractor.md) follows best practices for handling long-context tasks through chunking and state management, reducing the risk of context overflow while maintaining traceability.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:50 PM