ClawHub
Back to skill

Security audit

技术主管 一级验收与进度追踪

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only engineering review skill with no hidden code or dangerous behavior, though its broad trigger wording should be used carefully.

Install this for engineering acceptance and progress-review workflows where there are actual specialist outputs or acceptance artifacts to review. Be aware that some trigger terms are broad, so users should avoid invoking it for unrelated status or audit discussions. VirusTotal was pending, but static scan, metadata, and artifact review found no executable or hidden behavior.

SkillSpector

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 (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill includes broad keyword-based invocation guidance such as acceptance, progress, checkpoint, and audit-related terms, which can cause the skill to be selected in contexts beyond its narrowly intended use. In an agent system, ambiguous routing increases the chance of mis-execution, inappropriate authority use, or review decisions being applied to the wrong task stream.

Static analysis

No suspicious patterns detected.