ClawHub
Back to skill

Security audit

business-opportunity-insight

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language business-opportunity analysis skill with broad trigger wording but no code execution, persistence, credential access, or hidden data handling.

Install this if you want a Chinese-language assistant pattern for startup opportunity analysis. Be aware it may be invoked for broadly commercial-looking links or ideas, so users who only want neutral summarization or translation may need to state that explicitly.

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

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly says it should be considered even when the user did not clearly request business-opportunity analysis, as long as the shared information might have commercial value. That creates an over-broad activation boundary and increases the chance the agent applies this skill to ordinary conversation or neutral link-sharing, causing unwanted inference, reframing, or collection of sensitive business context without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description is written as Chinese-language operation without giving the user a language choice or documenting that the skill is locale-specific. While not directly dangerous like code execution, it can override user preference, cause misunderstandings, and reduce transparency if invoked for users expecting another language.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger scenarios are broad and open-ended, covering links, product descriptions, ideas, trends, and general information extraction, without clear exclusions. In practice this can cause skill overreach, where the system routes many unrelated or ambiguous user inputs into entrepreneurial analysis, leading to poor consent, misalignment with user goals, and possible exposure of sensitive strategic information to an unnecessary transformation step.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.