ClawHub

Config Sync — 16 AI Tools, 1 Source

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward local config generator that reads project rules and writes assistant config files, with no hidden network, credential, or destructive behavior found.

Install only if you want a repo-level assistant config generator. Run with --dry-run first, use --tools to limit outputs, and review or back up existing files such as AGENTS.md, GEMINI.md, .cursor/rules/config-sync.mdc, and .github/copilot-instructions.md before a non-dry-run execution.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill clearly instructs users to read canonical rule files and generate multiple output files, which implies filesystem read/write behavior, but it does not declare those capabilities or permissions explicitly. This weakens transparency and reviewability, making it easier for a user or orchestrator to invoke a repository-wide write operation without understanding the scope of file modifications.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The activation phrases are broad and map to common natural-language requests like 'sync configs' or 'generate ai rules' without clear constraints on repository scope, target files, or overwrite behavior. That can cause accidental activation in unrelated conversations and lead to unintended mass rewriting of configuration files across a project.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The description emphasizes convenience but does not clearly warn that execution may create or overwrite many configuration files in the repository. In context, this increases the risk of destructive or surprising changes, especially because the tool targets many assistant-specific files and defaults to generating all formats.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal