Back to skill

Security audit

数学教案设计

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign because the completed scan reported no AIG findings and the two low-confidence Skillspector findings were treated as expected for its purpose, though overall confidence is medium and coverage is partial.

The verdict is benign, but confidence is medium. Consider the class-level statistics scope note before installing. Skillspector scanned all 17 listed components but marked its analysis partial because three local references could not be resolved; those references were not fully covered by the scan.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

The reference instructs the lesson planner to calculate class-level error proportions, despite the manifest explicitly excluding class error statistics.

Medium
Category
Excessive Agency
Confidence
95% confidence
Finding

L227–L228 direct the skill to calculate error proportions from actual class homework summaries or item scores and report the sample size and source. This goes beyond anticipating errors during lesson preparation and enters class-level error statistics, which the manifest explicitly delegates to xiaozhi-teach-math-error-analyzer.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.