ClawHub
Back to skill

Security audit

max-research

Security checks for vulnerabilities and agentic risk

Overview

This is a research-process skill that asks agents to do exhaustive multi-source investigation, with no bundled code, persistence, credential use, or hidden execution behavior.

Install this only if you want a very time- and source-intensive research workflow. It may use many searches, inspect relevant local context, and produce long reports; users should clarify language/source preferences and scope before invoking it on sensitive or narrowly bounded tasks.

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
95% confidence
Finding

The skill explicitly requires English-first searching and only later adds Chinese/local-language searches, without offering the user a language preference. This can degrade accessibility, misalign with user intent, and bias research quality for users whose primary sources or regulatory context are in another language. In a research skill, hardcoding language behavior is more dangerous than in a narrow internal workflow because it systematically shapes evidence collection and conclusions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.