ClawHub
Back to skill

Security audit

LinkedIn Lead Gen Outreach

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent LinkedIn lead workflow with local CSV utilities, but users should handle exported prospect data and spreadsheet imports carefully.

Install only if you are comfortable using it for review-first lead research. Keep prospect exports limited to necessary business data, store them securely, delete them when no longer needed, and sanitize CSV cells before opening externally sourced lead data in Google Sheets or Excel.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/csv_builder.py:53
Finding

CSV Formula Injection in Spreadsheet-Bound Lead Exports

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill references local scripts that read and write files (scripts/csv_builder.py, scripts/sheets_prep.py, scripts/dashboard_stats.py) but does not declare any explicit tool scope or permissions. In an agent environment, this can lead to overbroad filesystem access assumptions, making it easier for the skill to read unintended files or write sensitive prospect data to unexpected locations without clear operator review.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill is designed to collect, score, message, and export personal prospect data, including names, LinkedIn URLs, titles, locations, and personalization signals, yet it does not warn users about privacy, lawful basis, retention, or safe handling of exported data. This increases the risk of inappropriate collection, oversharing, or insecure storage of personal data during lead-generation workflows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.