Back to skill

Security audit

Lobster Subagent Dev

Security checks for vulnerabilities and agentic risk

Overview

This is a small instruction-only development workflow skill that tells an agent to use subagents for implementation and review, with no hidden code or credential access.

Install this if you want an agent workflow that delegates implementation and review to subagents. Because the workflow can lead to code changes, test runs, model usage, and commits, use it with normal repository safeguards such as reviewing diffs and requiring approval for commits or high-impact commands.

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

Static analysis

No suspicious patterns detected.