ClawHub
Back to skill

Security audit

Reminder Guardian

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a normal local reminder helper, but its script computes the helper path incorrectly and may execute Python code outside the reviewed skill package.

Review or fix the time-helper path before installing or running this skill. If you use it, avoid putting secrets in reminder text, inspect the generated cron blueprint before adding it, and remove reminder log entries or scheduled jobs when they are no longer needed.

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
89% confidence
Finding
The skill appears to have operational capabilities to read files, write files, and invoke the shell, but no corresponding permissions are declared. That mismatch is dangerous because it hides the true trust boundary from users and reviewers, and shell access combined with file I/O can enable arbitrary command execution, data access, or persistence if the skill logic is compromised or abused.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.