Security audit
Pt Plan Of Care Drafter
Security checks for vulnerabilities and agentic risk
Overview
This is a markdown-only clinical drafting aid that is clearly scoped to outpatient PT plans of care and repeatedly limits use to licensed review and PHI-minimized drafts.
Use this only with appropriate clinical oversight. It may involve PHI and payer-sensitive documentation, so users should provide only the minimum necessary patient details, avoid direct identifiers, and have a licensed PT verify clinical, payer, and regulatory conclusions before use.
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
- 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
Static analysis
No suspicious patterns detected.