ClawHub

Progress Reporter

Security checks across malware telemetry and agentic risk

Overview

This skill locally creates periodic progress reports for running OpenClaw tasks, which matches its stated purpose, but users should know task details may be saved on disk.

Install only if you are comfortable with task descriptions and recent log activity being written to local progress-report files. Avoid using it for highly sensitive work unless you manage file permissions, know who can read the workspace, and clean up old reports when they are no longer needed.

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 (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The README says the use cases are determined automatically from the skill's functionality, but it does not clearly state when the skill should be invoked or what user intents it serves. In an agent setting, vague activation guidance can cause inappropriate routing or unexpected invocation, which may lead to misuse of the skill or execution in contexts the user did not intend.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly configures automatic periodic reporting and writes detailed progress data, task contents, and logs to predictable file locations without any warning, access control guidance, or data minimization. This can expose sensitive task details, operational activity, and internal workflow information to unauthorized readers on the host or through downstream log collection.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrases are generic and include broad terms like "progress report" and "任务汇报" without any namespace, permission boundary, or contextual qualifier. This can cause accidental or unintended invocation by unrelated user messages, leading to unsolicited scheduled reporting behavior or task-state exposure in contexts where the user did not explicitly request this skill.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal