ClawHub
Back to skill

Security audit

Two Sample Mr Research Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed research-planning skill with no executable payload, persistence, credential use, or hidden high-impact behavior.

This skill is reasonable to install for MR research planning, but users should verify current GWAS availability and choose ancestry-matched datasets based on their research population rather than treating EUR datasets as universally appropriate.

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
Confidence
88% confidence
Finding
This markdown file includes natural-language guidance that instructs users to default to EUR datasets for primary analysis. Under the policy rule, forcing a specific population/locale preference without explicit user choice or a narrowly documented scope can be a natural-language policy violation.

Static analysis

No suspicious patterns detected.