Back to skill

Security audit

课堂互动教练

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign with medium confidence: scanners found no security alerts in the completed scan, while Skillspector flagged a possible mismatch between its assigned role and question-chain drafting instructions.

The verdict is benign, but the evidence is incomplete: Skillspector marked its analysis partial because several local references could not be resolved, and it noted the role-scope issue. Consider whether you are comfortable with the skill drafting question chains before installing; benign does not mean risk-free.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
Findings (1)

The skill generates complete question-chain drafts despite the manifest assigning that responsibility to lesson-planner.

Medium
Category
Excessive Agency
Confidence
97% confidence
Finding

The manifest at L003 delegates question-chain drafting to xiaozhi-teach-lesson-planner, and L104 explicitly routes requests for question chains there. However, L258–L259 instruct this skill to generate a draft itself when none exists; L632–L634 repeat this fallback, extending its behavior beyond classroom implementation and follow-up questioning.

Content

No source excerpt is available for this finding.