Oathe Security Badge

Is SpillwaveSolutions/claude_permissions_skill safe?

https://github.com/SpillwaveSolutions/claude_permissions_skill

91
SAFE

This is a legitimate Claude Code permissions management skill that helps users configure CLI tools, file patterns, and project permissions through natural language. While it contains executable Python scripts and modifies agent settings, these serve documented purposes and include safety measures like automatic backups.

Category Scores

Prompt Injection 90/100 · 30%
Data Exfiltration 95/100 · 25%
Code Execution 80/100 · 20%
Clone Behavior 100/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 85/100 · 5%

Findings (3)

MEDIUM Executable Python Scripts Present -20 ▶

The skill contains three executable Python scripts (apply_permissions.py, detect_project.py, validate_config.py) that modify Claude Code settings. While these appear legitimate and serve the stated permissions management purpose, any executable code introduces potential security risks.

LOW Complex Workflow Routing Logic -10 ▶

The skill implements complex decision trees and workflow routing that could potentially be exploited in edge cases. However, the logic appears well-documented and serves legitimate permissions management purposes.

LOW Settings File Modification -5 ▶

Scripts modify Claude Code settings files which affects agent behavior. This is the intended functionality and includes backup mechanisms, but represents a form of persistent state modification.