Security audit
Web Automation Team — Agent Configuration Bundle
Security checks for vulnerabilities and agentic risk
Overview
This is a small, disclosed web-automation team skill with no bundled executable code, though users should be aware it can use browser, file, memory, agent, and MCP tools when available.
Install only if you want an agent team that can operate a browser and coordinate research/review work. Keep approvals enabled for purchases, account changes, financial actions, posting, or other sensitive site workflows, and be deliberate about allowing memory and generic MCP access.
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.