Back to skill

Security audit

data-source-evaluator

Security checks for vulnerabilities and agentic risk

Overview

This is a simple planning skill, but it explicitly asks the agent to include anti-scraping bypass strategy, which users should review carefully before installing.

Install only if you are comfortable with the agent discussing data collection strategy, and treat any scraping output as needing legal and terms-of-service review. Prefer official APIs, licensed datasets, permission-based access, rate limiting, and clear stop conditions when access controls are encountered.

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
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
95% confidence
Finding

The description says to invoke when the user asks about "数据源、数据采集、数据评估、数据策略、爬虫方案," which are broad topic keywords rather than a narrowly scoped trigger. It does not define boundaries or negative examples, so the skill could be invoked for many general conversations about data or scraping where this workflow is not intended.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly includes guidance for '反爬绕过' (anti-bot bypass) as part of the crawler plan, which normalizes evasion of technical protections and can facilitate unauthorized scraping or abuse of third-party services. Although the skill later says it must assess compliance and cannot recommend illegal collection, the bypass language materially increases risk by steering users toward defeating safeguards rather than using lawful alternatives.

Content

No source excerpt is available for this finding.