The Agent Skills Directory

[SAFE]: The skill operates entirely on local data using standard file formats like JSONL, YAML, and Markdown. No network-based exfiltration or external API calls are implemented in the provided scripts.
[SAFE]: Automation scripts located in agents/scripts/ utilize only standard Python libraries (json, os, pathlib, argparse) and are restricted to reading/writing data within the skill's directory structure.
[SAFE]: The installation script scripts/install.sh follows best practices by prompting the user for installation paths and performing standard file operations without requesting administrative privileges.
[SAFE]: The skill's architecture implements 'Progressive Disclosure,' which improves security by ensuring the AI agent only accesses specific modules relevant to the current task, thereby minimizing the attack surface for potential context-based exploits.
[SAFE]: No obfuscation, multi-layer encoding, or hidden instructions were found across the 46 files analyzed.

digital-brain