ClawHub
Back to skill

Security audit

lead-enrichment

Security checks for vulnerabilities and agentic risk

Overview

This skill provides disclosed B2B contact-enrichment guidance using public or user-authorized sources, with clear limits against bypassing access controls or collecting personal phone numbers.

Before installing, use this only for business contact enrichment on lists you are allowed to process, and confirm before running it on ambiguous 'find email' requests. Do not use it to scrape restricted platforms, bypass logins or captchas, or collect personal mobile numbers.

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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list includes broad natural-language phrases such as '找邮箱', '挖联系方式', and 'enrichment', which can match ordinary user requests outside a clearly intended sales-enrichment workflow. This creates a real risk of unintended invocation, causing the skill to activate on ambiguous prompts and initiate contact-harvesting behavior in contexts where the user did not explicitly mean to use this capability.

Static analysis

No suspicious patterns detected.