ClawHub
Back to skill

Security audit

Clawise

Security checks for vulnerabilities and agentic risk

Overview

The skill openly describes sensitive account-access services and contains only brief setup instructions, with no hidden code or automatic actions.

Before installing, treat this as a sensitive account-operations integration: use scoped or dedicated credentials where possible, avoid giving it unnecessary personal or account data, and review the provider's retention and security practices for email, SMS, vault, CAPTCHA, and identity workflows.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
91% confidence
Finding

The skill explicitly handles highly sensitive functions such as credential storage, email inboxes, phone verification, and identity management, but the user-facing description provides no warnings about sensitive data handling, least-privilege use, or the risks of supplying secrets and identity artifacts to the tool. In this context, the omission can mislead users or agents into over-sharing credentials or using the skill for risky account operations without adequate caution, increasing the chance of credential compromise or account abuse.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.