Security audit

Lobster Config Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a short Chinese-language configuration guide with no executable code, hidden data access, or persistence behavior.

Before using it, treat it as community configuration advice: only enable whitelist permissions for skills you actually need, keep AGENTS.md rules scoped to your intended behavior, and avoid changing system-prompt settings unless you understand the impact.

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: 88% confidence
Finding: The example AGENTS.md structure and surrounding instructions are entirely framed in Chinese and specify conversational style requirements without indicating that users may choose another language. This can amount to a language/locale policy violation because it implicitly forces one language absent opt-in or a documented region-specific justification.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.