ClawHub
Back to skill

Security audit

Reconnect

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed professional-networking helper that stores local project records and only performs LinkedIn outreach when the user has explicitly authorized it.

Install only if you are comfortable letting an agent research public professional profiles, maintain a local unencrypted project ledger, and use your browser session for LinkedIn actions after your explicit approval. Review each batch and stop if LinkedIn shows warnings, limits, or verification challenges.

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
  • 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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill instructs the agent to read and write project files, use browser/network-based research, and invoke a local helper script, but it does not declare corresponding permissions. This creates a capability/permission mismatch that can undermine policy enforcement and user understanding of what the skill is able to do, especially because it handles private project data and authenticated LinkedIn actions.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.