ClawHub
Back to skill

Security audit

Compare

Security checks for vulnerabilities and agentic risk

Overview

This comparison skill is coherent and low-risk, with a disclosed local preference file used to remember comparison priorities.

Before installing, be aware that the skill is designed to remember comparison priorities in preferences.md. Review or clear that file if you do not want future comparisons influenced by past preferences, especially for sensitive categories like career, finances, or providers.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs updating preferences.md after the interaction but does not mention obtaining user consent, notifying the user, or limiting what is stored. Silent persistence of user preferences can create privacy and profiling risks, especially if the preferences reflect sensitive interests or are reused across future sessions without the user's awareness.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.