ClawHub
Back to skill

Security audit

myatriumhealth-mcp

Security checks for vulnerabilities and agentic risk

Overview

This health-record reader requests access to login cookies despite assuring users those cookies stay inside the browser.

Review the cookie permissions before pairing. Ask the publisher to remove unused session-cookie and Cookie-header access or explain its necessity and correct the privacy assurance. Prefer scope limited to the portal host, confirm whose patient chart is active, and protect health information printed into agent or terminal logs. Revoke the persistent pairing when finished. The bundled files were fully reviewed, but the exact external CLI and extension builds remain unverified; no intentional exfiltration was established.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

The setup requests session-cookie header capture despite claiming the session cookie is never extracted.

High
Category
Excessive Agency
Confidence
94% confidence
Finding

The setup explicitly requests capture of the Cookie request header for my.atriumhealth.org despite assuring users that the session cookie is never extracted or stored. If honored by the bridge, this grant can expose HttpOnly authentication cookies outside their intended browser-only boundary; persistent pairing and access to sensitive medical records increase the consequences of bridge or CLI compromise. The supplied file does not establish actual cookie storage or exfiltration, but the requested capability is unnecessary for the described browser-side request relay.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md
--cookie '_Host-MyChartLocale' --cookie 'MYCPERS' --cookie 'p-MYC-LBPersistence' \
      --capture-header 'cookie@my.atriumhealth.org'

Then sign in to MyAtriumHealth in Chrome and run any command below. The first one
prints a pair code — approve it in the ContextMint Bridge popup. The trust persists.

## Use it