ClawHub
Back to skill

Security audit

marcus-linkedin-writer

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only LinkedIn writing helper with no code execution or persistence, though its activation wording is broader than ideal.

Install this only if you want a Marcus-specific LinkedIn writing style to be available. Because the trigger wording is broad, users should invoke it explicitly for Marcus's LinkedIn posts and review outputs before posting publicly.

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
95% confidence
Finding

The skill’s trigger conditions are broad enough to activate on common writing or content-creation requests, including generic phrases like 'write a post' and wide topical categories. This can cause inappropriate routing to a highly opinionated identity-specific writing engine, leading to misfires, incorrect persona use, and unintended disclosure or use of embedded business context when the user did not ask for this skill.

Content

No source excerpt is available for this finding.