Security audit
Structured Rads Report Drafter
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed radiology draft-reporting aid with strong guardrails and no code execution, persistence, or hidden data movement.
Install only if you want an AI assistant to help draft radiology reports for professional review. Do not provide patient names, MRNs, DOBs, SSNs, or unnecessary identifiers, and treat accession numbers as sensitive under your institution's policies. Outputs should remain drafts and be checked by a qualified radiologist before clinical 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.