ClawHub
Back to skill

Security audit

Linkedin Comment Drafter

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches a LinkedIn comment-drafting purpose, but it also includes guidance to make automated engagement look human and to use comments for sales prospecting cadence.

Review this before installing if you want a strictly neutral drafting aid. It can be acceptable for user-approved LinkedIn commenting, but you should remove or ignore the timing and sales-prospecting guidance unless your use complies with LinkedIn rules and your own standards for transparent engagement.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file expands the skill from drafting a comment on a pasted LinkedIn post URL into broader sales/prospecting workflows, including target-account engagement and recognition-building before outreach. That creates capability drift: the skill can be used to systematize influence and prospecting behavior beyond its declared scope, increasing abuse risk and making user intent less constrained.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The guidance to 'React before commenting, pause 8-15s, then comment' is not needed for drafting text and explicitly aims to make automation 'look human.' That encourages evasion of platform detection signals and operationalizes deceptive automated engagement, which can facilitate inauthentic activity and policy violations at scale.

Content

No source excerpt is available for this finding.