Back to skill

Security audit

开卷答题教练

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence: the scans report one medium-severity instruction-scope issue, while the other verdict dimensions are marked ok.

The verdict is benign, but consider whether the reported scope mismatch matters for your use. The scan covered all nine listed components; the finding concerns instruction scope, not reported code execution or persistence.

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 shared instructions relax the skill's methods-only restriction and permit solving specific questions.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

The shared guidance explicitly redefines all skills’ prohibition on providing original answers as merely withholding answers until the student has attempted the question, then permits escalation to worked explanations. This conflicts with this skill’s methods-only scope and could cause it to solve subject-specific questions rather than redirect them; however, the apparent purpose is educational scaffolding, and the demonstrated impact is limited to instructional scope bypass rather than data exposure or code execution.

Content

No source excerpt is available for this finding.