Security audit
Sud Treatment Plan Drafter
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed clinical drafting aid with strong draft-only and PHI-minimization boundaries and no executable behavior.
Use this only as a draft-support tool for qualified clinical staff. Avoid entering direct identifiers, confirm all diagnoses, codes, ASAM levels, and care recommendations manually, and do not place output into records or authorization workflows without licensed review and signature.
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