ClawHub
Back to skill

Security audit

新闻

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only news aggregation skill uses external retrieval but does not show hidden, destructive, or persistent behavior.

Install only if you are comfortable with the agent using your news topics or keywords to query external news, search, and possibly social-trending sources. Avoid entering sensitive private investigations, confidential business topics, or secrets as queries, and keep any API keys in environment variables rather than files or chats.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
78% confidence
Finding
Overly broad invocation guidance increases the chance the agent will activate this skill in contexts where the user did not intend external retrieval or topic expansion. In a skill with network-search behavior and exec listed as an available tool, vague triggers can cause unnecessary external access, privacy leakage of user queries, or unexpected behavior in adjacent tasks.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill performs retrieval from multiple external news sources but does not prominently warn users that their queries may be sent to third-party services. In context, this matters because user-provided topics may contain sensitive business interests, investigative themes, or personal subjects that should not be disclosed without clear consent.

Static analysis

No suspicious patterns detected.