ClawHub
Back to skill

Security audit

Fhir Upstream Proxy

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed FHIR proxy guide with expected healthcare-data forwarding behavior, but users should treat query parameters and audit logs as sensitive.

Before installing, confirm the configured FHIR server, auth model, audit retention, and compliance expectations. Use minimum-necessary search parameters because identifiers or PHI in query strings will be sent to the upstream server.

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
92% confidence
Finding

The skill explicitly states that all query parameters are forwarded upstream, but it does not warn users that anything placed in search parameters may be disclosed to the external FHIR server and logged there. In a healthcare context, query strings can contain identifiers, names, MRNs, dates of birth, or other sensitive data, so omission of that warning increases the risk of unintended PHI disclosure and privacy/compliance violations.

Content

No source excerpt is available for this finding.