Security audit
Lobster Cli Anything
Security checks for vulnerabilities and agentic risk
Overview
This skill gives straightforward instructions for building and validating a CLI harness, with no hidden execution, persistence, or data extraction behavior found.
Install this skill if you want an agent to help create CLI-Anything style harnesses. Expect it to read the source tree you point it at, possibly clone a GitHub repository you provide, create harness files, run tests, and perform a local editable Python install for validation; use a virtual environment when testing generated harnesses.
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
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