ClawHub
Back to skill

Security audit

Weekly Report Pro - Auto Collect, No Fluff

Security checks across malware telemetry and agentic risk

Overview

This skill is a local weekly-report helper that reads recent Git commit history for report material, with no evidence of upload, persistence, destructive behavior, or hidden actions.

Before using it, point the skill only at the code directories you want summarized and avoid sharing chat exports or task files that contain sensitive information unless you want that material included in the report.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill explicitly instructs the agent to run a local shell command and read from user-specified code directories, but it declares no permissions. That mismatch is dangerous because it can lead to unreviewed access to local repositories and metadata, and users may trigger file/system access without clear consent or sandboxing expectations.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The invocation examples include very broad phrases such as "周报" and "写日报", which are common natural-language requests and can easily collide with ordinary conversation. This increases the chance of unintended skill activation, causing the agent to prompt for local code directories and access Git history in situations where the user did not specifically intend to invoke this skill.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrases are broad enough to activate on generic requests like '周报' or '写日报', causing the skill to run in contexts where the user may only want writing help, not local repository inspection. In this skill, over-broad activation is more dangerous because activation can lead to shell execution and local file/repository access.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrase "写周报" is very generic and commonly used in ordinary conversation, so the skill may activate when the user is merely discussing weekly reports rather than explicitly requesting this tool. Because the skill can automatically scan local Git repositories and ingest other local materials, accidental activation broadens access to sensitive work data beyond clear user intent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.