ClawHub
Back to skill

Security audit

Linkedin Profile Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This is a LinkedIn profile writing-aid skill with no executable code or hidden account actions, though its trigger wording is broader than ideal.

Installers should use this for explicit LinkedIn profile audits or rewrites and review any generated public-facing profile text before posting. Treat the benchmark and uplift claims as marketing guidance unless independently verified.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Ae1

High
Category
analysis-evasion
Content
Global voice rules: see root `SKILL.md` §Voice rules. Additional skill-specific rules:
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list is broad enough to match routine profile-editing requests such as 'rewrite my headline' or 'fix my About,' which can cause the skill to activate in contexts where the user may not have intended this specific workflow. Over-broad activation increases the chance of incorrect routing, unnecessary collection of profile data, and interference with other more appropriate skills handling general writing or editing tasks.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The 'When to use' guidance is ambiguous and lacks clear exclusion criteria, especially for generic phrases like 'fix my headline' and 'optimize bio.' This can lead to unintended invocation on common editing requests outside LinkedIn, expanding the skill's operational scope beyond what users expect and increasing the risk of misapplication or unnecessary handling of personal profile content.

Static analysis

No suspicious patterns detected.