Drchrono

Security checks across malware telemetry and agentic risk

Overview

This DrChrono skill appears legitimate, but it gives an agent broad access to sensitive medical and billing records and record-changing actions without enough built-in safeguards.

Install only if you are authorized to connect DrChrono through Membrane and your organization permits that data path for healthcare records. Use a least-privileged account, verify OAuth scopes and revocation steps, and require explicit confirmation before creating, updating, deleting, billing, ordering, messaging, or exposing patient-record data.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (2)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The skill description is very broad for a high-sensitivity domain and could cause the agent to invoke the DrChrono integration for generic healthcare-related requests without clear user intent validation. In an EHR context, over-broad routing increases the chance of exposing or modifying PHI in response to ambiguous prompts.

Missing User Warnings

High

Confidence: 95% confidence
Finding: This skill handles highly sensitive PHI and supports record creation and modification, but the documentation does not include explicit warnings about privacy, authorization, or the risks of changing medical and billing data. Without these safeguards, an agent may access or alter regulated healthcare information without sufficient user confirmation or awareness.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal