ClawHub
Back to skill

Security audit

GitLab 每日提交汇总

Security checks across malware telemetry and agentic risk

Overview

This skill does the advertised GitLab-to-Feishu reporting, but it handles private repository data and credentials in ways that need review before use.

Review this before installing. Use --preview unless you intentionally want Feishu posting, fix or avoid the disabled TLS verification, store config.json securely, use a least-privilege read-only GitLab token, confirm the Feishu webhook recipients, and only enable cron/webhook/CI automation after explicit approval.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
89% confidence
Finding
The README includes a webhook receiver that invokes local commands via subprocess in response to remote HTTP requests. Even though the commands are hardcoded, this still introduces a remotely triggerable execution path and unsafe operational pattern that expands the attack surface beyond simple report generation, especially if the endpoint is exposed or the token check is weak or omitted in real deployments.

Missing User Warnings

Medium
Confidence
82% confidence
Finding
The README describes collecting data from private GitLab repositories and sending summaries to Feishu, but it does not warn users about potential disclosure of confidential code, issue, MR, or pipeline information to external chat systems. In this context, the absence of privacy guidance is security-relevant because the tool is explicitly designed to process private repository metadata and redistribute it.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README instructs users to create and place a GitLab Personal Access Token in config.json but does not warn against committing that file, sharing it, or storing secrets insecurely. This omission materially increases the chance of credential leakage, which could allow unauthorized access to private GitLab data and downstream systems such as Feishu webhooks.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.