ClawHub
Back to skill

Security audit

Git Distributed Todo

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Git-backed shared todo tool; it uses local shell, Git, and repository files in ways that match that purpose.

Install only if you are comfortable giving the agent shell access to run the bundled Python CLI and Git access to the shared todo repository. Use a dedicated repo, avoid putting secrets or private transcripts in task text, and designate only one notifier for reminders.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill instructs agents to execute a bundled Python CLI, read and write repository files, use environment variables, and invoke shell commands, but the manifest shown in SKILL.md does not declare corresponding permissions or capabilities. This creates a trust and sandboxing gap: a host may expose more power to the skill than operators expect, reducing reviewability and increasing the chance of unsafe execution in environments that rely on declared permissions for policy enforcement.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill enables implicit invocation for a capability that coordinates tasks through a shared Git repository, but the manifest provides no narrow trigger conditions or user-confirmation guardrails. This can cause the skill to activate in broader contexts than intended, increasing the chance of unintended repository interactions, cross-agent task leakage, or unauthorized actions based on ambiguous user requests.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.