Security audit
Interdisciplinary Care Plan Drafter
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed draft-documentation aid for hospice care plans, with strong reminders to avoid direct identifiers and require licensed clinical review.
Install only in an environment appropriate for healthcare information. Users should avoid entering direct patient identifiers, treat every output as a draft, and require licensed clinician and interdisciplinary team review before medical record entry, care delivery, or billing 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
