ClawHub
Back to skill

Security audit

Ai Trends Reporter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI-news and skill-recommendation helper with expected web/API use and local installed-skill listing, but it is mostly an agent instruction wrapper rather than a fully implemented script.

Install only if you are comfortable providing a Brave Search API key and, optionally, a ClawHub token. Expect the skill to use network search and inspect your installed OpenClaw skill names to tailor recommendations; ask for confirmation before enabling any recurring report workflow.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The declared description promises an automated generator that searches for recent AI news, searches ClawHub, compares against skills the user has not installed, and produces a structured report. The supplied code only reads the local skills directory to list installed skills and outputs informational placeholder text saying the real work must be done by an AI agent. This is a material description-behavior mismatch because the primary advertised capabilities are not implemented in the code chunk. The local filesystem access to enumerate installed skills is related to the stated goal, but the core functionality is absent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation phrases are broad and could cause the skill to trigger on ordinary requests about AI news or reports without the user clearly intending to invoke this specific skill. In an agent ecosystem, ambiguous activation can lead to unintended network access, workspace inspection for installed skills, and disclosure of recommendations or derived user preferences.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The usage examples are generic enough to overlap with normal assistant requests such as generating an AI trends report or setting a recurring task. This increases the chance of overbroad invocation and unintended execution of actions like web searches, ClawHub queries, or automated scheduling beyond what the user expected.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file contains user-facing comments and terminal messages in Chinese, including usage/status output, with no indication that the skill is region-specific or that users can opt into another language. This creates a natural-language locale policy issue because the skill effectively enforces a specific language by default.

Content

No source excerpt is available for this finding.