ClawHub
Back to skill

Security audit

market-intel

Security checks for vulnerabilities and agentic risk

Overview

This skill is a market-news briefing workflow that fetches and verifies public market data without hidden persistence, credential use, or destructive behavior.

Install this if you want a structured market-intelligence briefing assistant. Expect it to use current public market/news sources and possibly another market skill; verify citations and remember it is designed for factual briefing, not investment advice or trade execution.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The manifest says the skill triggers when the user 'needs to obtain market intelligence, understand overnight external markets, scan macro news, or track intraday capital flows and block trades,' which is a broad natural-language condition. Although examples are listed, the activation scope is still ambiguous because it does not clearly define boundaries or exclusions for when ordinary market-related conversation should not invoke the skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
70% confidence
Finding

The file mixes Chinese-only operational description with English triggers such as 'market intel' and 'overnight,' but does not explain whether outputs or interactions are constrained to Chinese or whether users may choose a language. This can create a language-policy issue because the skill implicitly favors one locale without documenting opt-in or offering a choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.