Security audit

Two Sample Mr Research Planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed markdown planner for Mendelian randomization study design and does not install code, persist changes, or access private data.

Before relying on outputs, choose GWAS datasets that match the target study population and treat the EUR default as a methodological starting point only when appropriate, not as a universal rule.

A.I.G

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

SkillSpector

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

Findings (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: This markdown file contains natural-language guidance that instructs users to 'Default to European ancestry (EUR)' when available. Under the policy rule, forcing or prioritizing a specific population/locale without explicit user opt-in or a clearly bounded justification can be a natural-language policy concern, especially since the recommendation is framed as a default rather than a user-selected option.
Content: No source excerpt is available for this finding.