Security audit
ai-first-cli
Security checks for vulnerabilities and agentic risk
Overview
This skill provides coherent CLI design guidance without requesting sensitive access or automatic execution.
Use this as design guidance. Preserve user authorization for destructive actions when adding noninteractive flags, and implement the validation and dry-run safeguards discussed in its [cited CLI source](https://justin.poehnelt.com/posts/rewrite-your-cli-for-ai-agents/).
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
