Back to skill

Security audit

starborne

Security checks for vulnerabilities and agentic risk

Overview

This local space game uses purpose-aligned game saves, with no evidence of credential access, external data sharing, or unrelated system changes.

Expect local game saves and a fixed English introduction. The play.py launcher stores saves beside the scripts; running the engine directly uses /workspace/starborne. Back up saves before deleting, selling, dismantling, or clearing inventory. Some documented gameplay rules differ from the bundled scripts.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The skill mandates an English-only opening without user language opt-in.

Low
Category
Output Handling
Confidence
93% confidence
Finding

The instructions require the exact two English sentences at the start of every new session or reset. This imposes English for that portion of the response without offering a language choice or documenting a locale-specific justification.

Content

No source excerpt is available for this finding.