Back to skill

Security audit

OpenClaw Task Progress Tracker

Security checks across malware telemetry and agentic risk

Overview

This skill is a file-based task/project progress tracker with disclosed workspace writes and no executable code or external service behavior.

Install this if you want the agent to maintain local task/project progress files. Before using document attachment, tell the agent whether to copy, move, or only reference source files; before completing items, expect a short memory note to be written for later distillation.

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Medium
Confidence
90% confidence
Finding
The template instructs the agent to write to a separate memory/YYYY-MM-DD.md file when a task is completed, which expands behavior beyond the declared tasks/ and projects/ tracking scope. This creates an implicit cross-directory write path that could cause unintended data persistence, scope creep, or writes into a more sensitive journal area without explicit user approval.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly allows moving documents from outside the task/project directory into an internal docs/ folder without requiring a clear user confirmation or warning that the original file location will change. In an agent setting, this can unexpectedly alter workspace layout, break references, or relocate user files in ways the user did not intend, especially when the source path is shared with other workflows.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.