Security audit

lead-scraper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed lead-scraping helper, but it asks agents to collect and export contact data across broad sources without enough scoping or user-control requirements.

Review this skill before installing. Use it only for public, legally permitted sources; avoid private profiles or sensitive personal data; confirm platform terms, consent, retention, access controls, and export fields before collecting or syncing leads to a CRM.

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 (3)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill promotes export to Excel/CSV/JSON/CRM and lead scoring, but does not present a prominent warning about handling personal and business contact data before encouraging collection and export. Because the skill is explicitly designed to aggregate, enrich, rank, and export contact information, missing upfront safeguards can facilitate privacy violations, unlawful marketing use, or insecure downstream sharing of personal data.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The invocation examples use broad natural-language commands like '抓取…企业联系方式' and '从LinkedIn抓取…线索' without clear trigger boundaries, scope limits, or disallowed targets. In a scraping skill that handles contact data across multiple platforms, this increases the chance the agent will over-collect personal/business data, act on ambiguous user requests, or perform collection on sources whose terms or privacy settings should block scraping.

Natural-Language Policy Violations

Low

Confidence: 81% confidence
Finding: All user-facing instructions, examples, and warnings in the file are presented only in Chinese, effectively imposing a single language on users without an opt-in or documented regional scope. Under the policy, a forced language or locale without user choice or clear justification is a natural-language policy issue.

Static analysis

No suspicious patterns detected.