ClawHub
Back to skill

Security audit

Baa Review

Security checks for vulnerabilities and agentic risk

Overview

This is a focused BAA review skill that reads user-provided agreements and returns a structured compliance assessment, with no hidden execution or persistence found.

Before installing or using this skill, treat BAAs as sensitive legal and healthcare-adjacent documents. Provide only the agreement needed for review, redact patient identifiers or unnecessary confidential business details where possible, and verify any legal recommendations with qualified counsel.

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
90% confidence
Finding

This skill is explicitly designed to ingest and analyze Business Associate Agreements, which often contain protected health information or other sensitive healthcare/vendor data, yet the skill provides no user-facing warning or handling guidance about submitting PHI-sensitive content. That omission can cause users to paste regulated data into an analysis workflow without understanding privacy, retention, or minimization implications, increasing the risk of inappropriate disclosure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.