ClawHub
Back to skill

Security audit

Merge Check Paid

Security checks across malware telemetry and agentic risk

Overview

This appears to be a PR merge-analysis skill, but it combines broad activation language with shell/write access, GitHub credentials, and CI gate behavior that is not tightly scoped.

Review this skill before installing if it will run in repositories with private code or tokens. Use least-privilege GitHub credentials, avoid broad PATs, require confirmation before any CI gate or blocking action, and only invoke it for PR merge-analysis workflows rather than general data analysis.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
86% confidence
Finding
The activation text is overly broad, including generic data analysis, reporting, statistics, and visualization language unrelated to merge checking. In an agent system with read/exec/write tools, this can cause the skill to trigger for common requests outside its intended scope, increasing the chance of unnecessary command execution, repository access, or handling of sensitive data under the wrong skill.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The documentation says the skill supports Chinese interaction and presents that as a default behavioral expectation without user opt-in. Forced language behavior can override user intent, reduce transparency, and increase the risk that a user misunderstands security-relevant prompts, repository actions, or command outputs when the agent has execution capabilities.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.