ClawHub
Back to skill

Security audit

News Specialist

Security checks for vulnerabilities and agentic risk

Overview

This is a plain news-analysis skill that asks the agent to use reliable retrieved news when needed and does not include code, persistence, credential handling, or hidden behavior.

Before installing, understand that this skill may activate for many current-events or trending-topic questions and may use news retrieval when the conversation lacks enough context. That behavior is expected for the skill; users should still ask for sources and be cautious with commentary or predictions on developing stories.

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
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill advertises itself for a very broad set of common news-related requests, including explanations, commentary, predictions, and trending topics. This can cause over-activation and routing collisions with more specialized skills, leading to inappropriate delegation, unnecessary retrieval, and increased exposure to untrusted external content during ordinary conversation.

Content

No source excerpt is available for this finding.