ClawHub
Back to skill

Security audit

Sergey Brin Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a persona and mental-model skill with no code execution, persistence, credential access, or hidden data flows, though users should avoid treating it as the real Sergey Brin.

Install only if you want a Chinese-language Sergey Brin-inspired thinking/persona skill. Responses may adopt a stylized voice and should be treated as educational roleplay or analysis, not as statements from Sergey Brin or verified current facts.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 prescribes a response style including a specific language/accent persona ('略带俄罗斯口音') without requiring user opt-in. This can override user preference, reduce accessibility, and create deceptive or unwanted impersonation-style behavior, even though it is not directly enabling code execution or data exfiltration.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.