ClawHub
Back to skill

Security audit

Visual Content Desc

Security checks for vulnerabilities and agentic risk

Overview

The skill is a simple, disclosed helper for describing medical visuals, with privacy cautions needed for clinical data but no evidence of hidden, networked, persistent, or destructive behavior.

Use this only with medical images you are authorized to process. De-identify patient information where possible, keep outputs in approved workspace locations, and verify your privacy/compliance obligations before using it on clinical or regulated data.

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
92% confidence
Finding

The skill is explicitly designed to describe medical images and charts, which commonly contain protected health information or other sensitive clinical context. Omitting a clear warning about sensitive health data handling can lead users to process regulated data without appropriate caution, increasing the risk of privacy, compliance, and data minimization failures.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.