ClawHub
Back to skill

Security audit

X Hot Topics Daily

Security checks for vulnerabilities and agentic risk

Overview

This is a transparent X trend-summary skill with some scoping and language-preference caveats, but no hidden execution, persistence, or destructive behavior.

Install only if you want an agent to use a browser, likely with your existing Chrome/X session, to read X search and feed results for daily-style Chinese briefings. Review outputs for accuracy because X trends can include rumors or low-quality posts, even though the skill instructs filtering.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description and usage scope are broad enough that the skill could activate on routine requests about X/Twitter summaries or trend monitoring, not just when the user explicitly wants this exact workflow. Over-broad activation can cause inappropriate tool use, unexpected browsing to external sites, and application of this skill’s opinionated output format when a simpler or safer response was intended.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Mandating Chinese output regardless of user preference can override the user’s requested language and reduce transparency, especially in multilingual or accessibility-sensitive contexts. While not directly enabling code execution or data exfiltration, it is still a policy and safety weakness because it constrains user control and may cause miscommunication in a browser-driven information gathering workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The quick trigger phrases include generic requests like getting today's hot news overview across five topics, which could match normal summarization tasks and unintentionally invoke this skill. That creates a control-boundary problem: the system may browse X, use a fixed topic set, and produce a constrained anti-FOMO format even when the user did not request those behaviors.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.