ClawHub
Back to skill

Security audit

OGT Docs Create Task

Security checks across malware telemetry and agentic risk

Overview

This skill is a docs workflow helper that creates and moves task-tracking files inside a repository, with no evidence of hidden payloads, credential access, exfiltration, or unrelated behavior.

Install this only in repositories where you want an agent to create, update, and move task folders under docs/todo. Review the generated file changes before treating tasks as done, rejected, or implemented if you need tight control over workflow state.

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
89% confidence
Finding
The skill description is broad enough to match generic task-management requests, which can cause the agent to invoke a repository-modifying workflow in situations where the user may not have intended file-system changes. Because this skill creates, moves, and edits files across workflow stages, overbroad triggering increases the risk of unintended state changes and documentation churn.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The workflow contains concrete commands to move directories, touch files, and write content, but it does not require any user-facing warning or confirmation before modifying repository state. In an automated agent context, this can lead to silent or surprising changes to tracked files, especially when triggered from high-level requests that sound informational rather than operational.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.