ClawHub
Back to skill

Security audit

Publish Safe PRs

Security checks across malware telemetry and agentic risk

Overview

This skill helps sanitize public GitHub contributions and requires explicit approval before posting or editing anything public.

Before installing, understand that this skill is designed for public GitHub work: only approve publication after reviewing the exact draft, destination, identity, attachments, and fetched public result. Keep deny-term files private and do not rely on the scanner alone for sensitive disclosures.

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
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical
Code
suspicious.dynamic_code_execution
Location
tests/test_publication_preflight.py:15