ClawHub
Back to skill

Security audit

Two Sample Mr Research Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a research-planning skill for Mendelian randomization studies, with no executable code, persistence, credential handling, or hidden behavior found.

Before installing, understand that this skill helps draft research plans and code templates, not validate specific GWAS IDs or guarantee scientific correctness. Users should verify current database releases, choose ancestry-matched datasets appropriate to their study population, and avoid overinterpreting causal claims when instruments are weak or datasets are mismatched.

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

Low
Confidence
83% confidence
Finding
The document instructs users to 'Default to European ancestry (EUR) GWAS pairs for primary analysis when available,' which is a natural-language preference for a specific population grouping. While a technical rationale is given, it is phrased as a default rather than as a user choice or context-specific option, which can be read as a locale/population policy constraint.

Static analysis

No suspicious patterns detected.