ClawHub
Back to skill

Security audit

competitor-alert-system

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed competitor-monitoring skill that relies on public web sources, with the main caution that monitored company lists may be sensitive when searched externally.

Install only if you are comfortable using external search and business-data sources for the competitor names, domains, and topics you provide. Avoid entering confidential target lists or non-public strategy details unless your environment permits that, and approve any Cron-based monitoring or push alerts deliberately.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs broad competitor monitoring, continuous collection, and real-time push behavior, but it does not clearly warn users that supplied company names, domains, and monitoring targets may be queried against external services and could reveal the user's research interests. In a business-intelligence context, those targets can themselves be sensitive, and silent external querying creates privacy, confidentiality, and compliance risk even if the sources are public.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The data sources section lists multiple third-party platforms but does not disclose that user-provided competitor lists and monitoring parameters may be transmitted to those services during collection. This omission is risky because monitoring targets can expose strategic plans, client interests, investment theses, or internal market research, especially when automated recurring queries are performed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill description, triggers, workflow, and examples are entirely in Chinese, and there is no indication that users can choose another language or that the skill is intentionally restricted to a Chinese-language or region-specific context. This creates a natural-language locale constraint without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.