ClawHub
Back to skill

Security audit

English Practice

Security checks for vulnerabilities and agentic risk

Overview

This English workbook skill is not malicious, but it should be reviewed because it directs users to a plaintext IP-based API that includes answer-key and question-bank operations without documented access controls.

Before installing or following this skill, verify who operates the API, require HTTPS on a named domain, avoid submitting student data or private materials, and ensure answer-key and teacher-PDF endpoints are protected by authentication and authorization.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:392
Finding

Cleartext Communication with an Unverified External API

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
SKILL.md:511
Finding

Unpinned Third-Party Python Dependencies

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill explicitly supports teacher PDFs containing answers and answer-key retrieval, but it provides no indication that these outputs are sensitive and must be limited to authorized users. In an educational testing context, unrestricted access can enable students or unauthorized parties to obtain answer keys, undermining assessment integrity.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The documented endpoints /api/pdf/generate/{paper_id} and /api/answer-key/{paper_id} expose sensitive exam materials, yet the skill description omits any mention of access control, authorization, or protection of educational content. If implemented as documented, users who can guess or obtain a paper_id may retrieve protected materials without approval.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 406)May include surrounding context.

生成练习册请求示例

bash
curl -X POST http://101.34.62.112:8083/api/practice/generate \
  -H "Content-Type: application/json" \
  -d '{
    "version": "外研版",

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
71% confidence
Finding

SQP-3 covers language or locale policy violations when a skill forces a specific language without user opt-in. The title and throughout the document define the skill as generating English exercises only, with no indication that users can choose another language or explicitly opt into this constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.