ClawHub
Back to skill

Security audit

LobsterBio - Dev

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only Lobster AI development skill with coherent, disclosed guidance and no hidden execution behavior.

Install this when you work on the Lobster AI codebase. Be aware that its broad trigger phrases may make it appear during unrelated development requests, so confirm the task is actually Lobster-related before relying on its guidance.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Instruction Override

High
Category
Prompt Injection
Content
--workspace, -w PATH    Set workspace directory
  --model, -m MODEL       LLM model to use (default: from config)
  --verbose, -v           Enable verbose output
  --debug                 Enable debug mode
```

**In-chat commands:**
Confidence
70% confidence
Finding
This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list includes generic phrases such as "contribute," "fix bug," "add feature," and "write tests," which can match many ordinary software-development requests unrelated to Lobster AI. This can cause the skill to activate outside its intended scope, increasing the chance that users receive domain-specific guidance in the wrong context or that broader repository instructions are inappropriately injected into unrelated tasks.

Static analysis

No suspicious patterns detected.