ClawHub
Back to skill

Security audit

Profile Optimization

Security checks for vulnerabilities and agentic risk

Overview

This is an advisory social profile optimization skill with no executable code and no authority to edit accounts directly.

Installers should know this skill may activate on broad profile/bio wording, so review whether that routing is acceptable. Its output is copy and recommendations for the user to apply manually; it should not be treated as able to update social accounts or verify analytics itself.

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
Confidence
93% confidence
Finding
The trigger description includes very broad terms such as "profile" and common phrases like "write my bio," which can cause the skill to activate in contexts unrelated to social media profile optimization. Over-broad invocation increases the chance of unintended routing, privacy overreach into unrelated user requests, and interference with more appropriate skills, even though the content itself is not otherwise malicious.

Static analysis

No suspicious patterns detected.