ClawHub
Back to skill

Security audit

高等数学学情数据分析Skill

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent, but it profiles identifiable student performance and risk data without clear privacy, authorization, or handling safeguards.

Install only for authorized educational use. Treat student names, IDs, scores, rankings, submission behavior, and risk predictions as sensitive records; prefer de-identified inputs and restrict exports or screenshots to appropriate staff.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill is explicitly designed to process sensitive student educational records, including performance, rankings, and risk alerts, but it provides no privacy notice, access-control expectations, consent requirements, or data-handling safeguards. In an education context, this increases the chance of unauthorized disclosure, over-collection, or misuse of student data, which can create regulatory, ethical, and reputational risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The example student profile includes directly identifying information and sensitive educational metrics such as name, class, percentile/rank, weak topics, submission behavior, and risk-related inferences, yet it is presented without any warning about restricted handling or redaction. Sample payloads often get copied into real workflows, so this normalizes exposing student PII and academic profiling data in logs, demos, screenshots, and downstream integrations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language instructions, descriptions, and examples are entirely in Chinese, which effectively imposes a specific language on users. The policy allows locale constraints only when users are given a choice or the restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.