ClawHub
Back to skill

Security audit

Yq Industry Research Report

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a report-generation skill whose file creation and document output behavior fit its stated purpose, with no evidence of malicious activity.

Install only if you want an agent to generate report files and formatted deliverables. Before running it, be explicit about whether you want files created, where outputs should go, and whether you want DOCX/PDF conversion or just an in-chat research summary.

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 (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger keywords are extremely broad and cover common terms like research report, industry analysis, market research, and trends, which can cause the skill to activate for many ordinary analytical queries. This increases the chance of unintended invocation, causing the agent to enter a heavyweight file-writing workflow and potentially perform actions the user did not expect.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill mandates creating and modifying multiple files, generating charts, and converting documents to DOCX/PDF, but it does not require explicit user notice or confirmation before performing these side effects. In practice, this can lead to unexpected filesystem changes, resource consumption, and persistent artifact creation from what may have begun as a simple informational request.

Static analysis

No suspicious patterns detected.