Security audit
SurfAgent Browser Operations
Security checks for vulnerabilities and agentic risk
Overview
This skill is a plain browser-automation guidance document that emphasizes tab hygiene, visible verification, and cautious fallback behavior, with no bundled code or hidden execution path.
Install only if you want an agent to follow disciplined browser-operation practices. Because the skill is meant for browser agents, it may guide work inside already logged-in browser sessions; review actions involving email, social posting, settings changes, or account identity before allowing them, and avoid storing sensitive details in any state-map notes.
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
