Security audit
Lobster Search First
Security checks for vulnerabilities and agentic risk
Overview
This is a documentation-only workflow skill that tells an agent to research existing tools before coding, with no executable payload or hidden install behavior.
Reasonable to install if you want agents to look for existing tools before writing custom code. Review any proposed package, MCP, or configuration changes before accepting them, and avoid putting secrets or sensitive private data into research prompts.
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.