ClawHub
Back to skill

Security audit

Linkedin Ghostwriting

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent LinkedIn ghostwriting skill that asks for business context and produces marketing copy, with no evidence of hidden execution, exfiltration, persistence, or destructive behavior.

Before installing, expect the skill to ask for specific business results, audiences, CTAs, and publicly claimable metrics, and review any generated LinkedIn copy before posting. Be aware it may route the draft through a separate humanizer-style skill if one is available.

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill’s invocation description is broad enough to match many generic writing-assistance requests, which can cause the agent to select this specialized skill in contexts where it is not appropriate. That creates prompt-routing risk: users asking for ordinary writing help may be funneled into a persuasive ghostwriting workflow, increasing the chance of irrelevant behavior, unnecessary data collection, or unintended style/strategy shaping.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.