ClawHub
Back to skill

Security audit

News Sentiment Analysis

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language A-share news sentiment guide with no code execution, persistence, credential access, or data movement.

Use this as a market-news interpretation aid, not as personalized investment advice. Be especially cautious because the skill includes direct trading suggestions such as heavy-position chasing, and its broad trigger phrase may activate when you did not intend to request stock analysis.

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 (2)

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The entire skill description, rules, and trigger examples are written only in Chinese, with no indication that the user may choose another language or that the skill is intentionally restricted to a Chinese-only audience. Under the stated policy, a language or locale constraint should be opt-in or clearly justified.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrase examples are very broad, short, and resemble ordinary user conversation, which can cause the skill to activate unintentionally during unrelated chats. In a finance-oriented skill, accidental invocation is more concerning because it may inject trading guidance or sentiment framing into general discussions, increasing the risk of inappropriate or overconfident investment advice.

Static analysis

No suspicious patterns detected.