Security audit
ai-skill
Security checks for vulnerabilities and agentic risk
Overview
This is a straightforward coding-assistant skill for Next.js and FastAPI, with broad but disclosed development capabilities and no hidden execution or persistence.
Before installing, understand that this skill is meant to help edit and analyze code and may use shell commands, file operations, and network access as part of that work. Those capabilities are expected for the stated purpose, but you should keep normal review control over project mutations, dependency installs, and any command that touches secrets or production resources.
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
Static analysis
No suspicious patterns detected.