ClawHub
Back to skill

Security audit

Post Summarizer

Security checks across malware telemetry and agentic risk

Overview

This skill is a public news and article summarizer with some broad trigger phrases, but its behavior is disclosed and limited to web search/fetch summarization.

Install this if you want Chinese-language summaries of public news and articles. Use explicit news sources, article URLs, or clear news-summary wording to avoid accidental activation; the reviewed artifacts do not show local data access, credential handling, persistence, or destructive behavior.

SkillSpector

By NVIDIA
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 (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description uses broad triggers like '帮我看XX新闻', '总结这篇', and '最新XX资讯', which can match many ordinary user requests and cause the skill to activate unexpectedly. Over-broad activation can hijack unrelated conversations, leading the agent to fetch external content or change task flow without sufficiently clear user intent.

Vague Triggers

Medium
Confidence
89% confidence
Finding
Mode A defines activation using vague phrases such as '帮我看XX', 'XX最新文章', and 'XX热点', which are ambiguous and may refer to many non-news tasks. This increases the chance of unintended invocation and unnecessary web access, which can override user intent or expose the agent to untrusted content more often than necessary.

Vague Triggers

Medium
Confidence
92% confidence
Finding
Mode E uses highly generic triggers like '快报', '最新十条', and '今天发生了什么', which are common conversational phrases and not safely scoped to this skill. Such generic triggers can cause accidental activation during general chat, leading to unsolicited browsing and summarization of external sources.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.