ClawHub
Back to skill

Security audit

LinkedIn Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-risk LinkedIn profile writing helper for healthcare professionals, with one overbroad routing phrase users should treat cautiously.

Install only for healthcare LinkedIn/profile-branding work. Be aware that one sentence is worded broadly, so users or agents should avoid invoking it for unrelated writing, research, clinical advice, or general formatting tasks.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The guidance to use the skill for 'other tasks that require explicit assumptions, bounded scope, and a reproducible output format' is overly broad and can cause the agent to invoke this healthcare LinkedIn skill for many unrelated requests. That creates scope confusion and increases the chance the agent follows irrelevant instructions or produces incorrect outputs under the authority of the wrong skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger text broadens a healthcare LinkedIn optimization skill into 'other tasks that require explicit assumptions, bounded scope, and a reproducible output format,' which weakens routing constraints and can cause the agent to invoke the skill outside its intended domain. In practice, this increases the chance of scope drift, misleading outputs, and bypass of domain-specific safety boundaries that are only appropriate for profile-writing use cases.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.