ClawHub
Back to skill

Security audit

Phy Pre Commit Gen

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward pre-commit config generator with disclosed, user-run repository reads and config-file writes.

Use --dry-run first and review the generated .pre-commit-config.yaml before enabling it. Only use --overwrite when you intend to replace an existing config, and remember that later running pre-commit may fetch the pinned hook repositories and let formatters modify files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill clearly instructs the user to read project files and write a generated .pre-commit-config.yaml, yet the metadata shown in SKILL.md does not declare corresponding permissions. That mismatch weakens trust boundaries and informed consent: a platform or user may assume the skill is non-invasive when it can inspect repository contents and modify files.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.