ClawHub
Back to skill

Security audit

日语朗读作业批改模板

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Japanese reading homework grading skill, with disclosed local recordkeeping that teachers should treat as sensitive student data.

Install only for authorized teachers handling Japanese reading assignments. Store generated audio, score, report, and progress files in a restricted course folder, avoid unnecessary student identifiers where possible, and delete or archive the files according to school data-retention rules after grading is complete.

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
  • 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
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill explicitly instructs saving student scores, progress, failed-audio metadata, and per-student report files to local paths, but it provides no retention, access-control, minimization, or privacy guidance. Because this is student performance data and may include identifiers plus evaluation results, persistent storage increases the risk of unauthorized disclosure, accidental reuse, or over-retention.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The markdown mandates specific feedback wording and display conventions in Chinese/Japanese-context labels, but does not offer any language or locale choice for users. Under the policy, forcing a particular language/locale without opt-in is a natural-language policy violation unless the restriction is clearly documented and justified as region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.