ClawHub

Backlog Grooming

Security checks across malware telemetry and agentic risk

Overview

This skill is purpose-aligned, but it can trigger unscoped automated changes to Google Tasks through an external grooming plugin.

Review before installing. Confirm what `workflow_backlog_grooming` does, which Google account and task lists it can access, whether it may delete or complete tasks, and whether scheduled runs can require a preview or explicit confirmation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger condition is broad enough that a loosely phrased user request could cause the skill to autonomously invoke backlog grooming without a clear, explicit confirmation that task modifications are intended. In this context, the skill performs state-changing actions against Google Tasks, so ambiguity materially increases the risk of unintended deletions, completions, rescheduling, or other backlog modifications.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The description does not warn users that the skill will autonomously modify Google Tasks items, which can cause users to invoke it without understanding that it performs write actions rather than passive analysis. Because the skill is designed to run on schedule or on request, missing disclosure reduces informed consent and makes unintended task changes more likely.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal