Security audit
Cap Cancer Synoptic Report Drafter
Security checks for vulnerabilities and agentic risk
Overview
This skill is a narrowly scoped medical drafting aid that emphasizes qualified pathology review and does not contain code, persistence, or hidden data handling.
Install only for use by qualified pathology or LIS personnel. Do not treat its output as a signed diagnosis, staging decision, biomarker release, or patient-facing communication; all drafts should be reconciled against the applicable CAP protocol version and reviewed in the LIS by the attending pathologist.
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.