Back to skill

Security audit

博物馆看展 · Museum Explorer

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: the scanners reported no findings, though one test file was only partly interpreted and the install mechanism received a note.

The verdict is benign, but it is not a guarantee of safety. Skillspector's analysis was partial: 10 of 11 components were scanned, and interpretation of test/static.test.js was incomplete. Consider this coverage gap before installing.

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