ClawHub
Back to skill

Security audit

Challenger Thesis

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed investment-research prompt skill that gathers public company data and does not include code execution, persistence, credential use, or hidden behavior.

Install if you want a Chinese-language framework for public-company moat and challenger analysis. Expect it to use web searches and public financial sources; review outputs as research, not financial advice, and specify language, company, business segment, and depth when invoking it.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger conditions are broad enough to capture many generic requests such as 'analyze XX company' or 'is XX worth holding long term,' which can cause this skill to be invoked when a narrower or more appropriate skill should handle the task. In an agent setting, over-broad routing can lead to unintended web access, excessive data gathering, and misleading outputs because the skill assumes deep single-company investment research even when the user's intent is ambiguous.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The template tells users they can 'directly send to the agent to trigger challenger-thesis skill,' which encourages broad and automatic activation rather than careful routing. In this skill's context, the metadata already contains expansive trigger rules for many company-analysis requests, so this wording increases the chance the skill is invoked for borderline or unintended prompts, potentially bypassing user choice and causing mis-scoped analysis.

Natural-Language Policy Violations

Low
Confidence
97% confidence
Finding
Hard-coding 'LANG: 简体中文' in the runtime template overrides user language preference and can cause the agent to respond in a language the user did not request. While not a classic security exploit, it is a prompt-quality and control issue that may reduce transparency and informed use, especially if the surrounding system expects user-driven language selection.

Static analysis

No suspicious patterns detected.