ClawHub
Back to skill

Security audit

Non Tumor Ml Research Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a planning-only biomedical research skill with no executable code, persistence, credential use, or hidden data handling observed.

Installers should understand that this skill may activate for broad biomedical ML planning phrasing, so users should provide a clear non-cancer disease, mechanism, or diagnostic-biomarker goal. It does not appear to execute code or access private data by itself.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger guidance is unusually broad and includes casual phrases like 'I want to study X using machine learning,' which can cause the skill to activate for generic ML or research-planning requests that are not clearly within the intended biomedical/non-tumor scope. Over-broad activation can misroute user requests, suppress better-matched skills, and increase the chance that specialized biomedical planning is applied inappropriately to ambiguous or adjacent contexts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.