Back to skill

Security audit

CMS Star Ratings Clinical Intelligence

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent clinical decision support, but one patient-prioritization rule could disadvantage non-English-speaking members in a healthcare outreach workflow.

Review the MTM/CMR prioritization logic before installing or using this in live healthcare operations. In particular, replace the English-preference scoring advantage with an equitable language-access workflow, and verify current CMS specifications before relying on the clinical and Star Ratings timelines.

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
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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description says to use the skill for "any Medicare Part D Stars strategy question," which is broad and lacks clear boundaries on what is in scope versus out of scope. This can cause unintended invocation for a wide range of ordinary strategy discussions related to Part D, especially because no exclusion conditions or negative examples are provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The prioritization logic explicitly assigns positive points for members whose preferred language is English or when a bilingual pharmacist is available, which means English preference itself increases service priority. In a healthcare outreach workflow, this can systematically disadvantage patients with limited English proficiency and create discriminatory access to medication therapy management services, with downstream clinical and compliance risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.