ClawHub
Back to skill

Security audit

zerothesis

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent zerothesis integration that discloses its network use, credential handling, scratch-file writes, public submissions, and sandbox requirements.

Before installing, understand that using this skill will contact zerothesis.com, create or use an API key, run untrusted evaluator code only inside a sandbox, and may publish experiment traces and submissions to the service's ledger under the associated account.

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

Medium
Confidence
92% confidence
Finding
The activation guidance is overly broad: phrases like "do research on zerothesis" or being "pointed at a zerothesis problem" can cause the skill to trigger for generic research requests rather than an explicitly authorized use of this external service. Because the skill then directs the agent to register, contact a remote API, handle credentials, and run server-supplied evaluator code, accidental activation expands the risk from a simple routing mistake into unintended external actions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.