ClawHub
Back to skill

Security audit

墨灵高考作文批改

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward essay-correction skill that sends user-provided essay text to InkCraft as its disclosed core function.

Install only if you trust InkCraft with the essay prompt, essay body, and any optional reference text you provide. Use a revocable InkCraft API key, keep INKCRAFT_BASE_URL on the official service unless you intentionally trust another endpoint, and avoid submitting sensitive personal information unless you are comfortable sharing it with that service.

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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill sends user-provided essay content to an external InkCraft API, but the description does not clearly disclose that user text will leave the platform. This creates a data-transparency and privacy risk because users may submit sensitive personal or educational content without informed consent.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
BASE_URL="${INKCRAFT_BASE_URL:-https://www.inkcraft.cn}"
curl -sS -X POST "$BASE_URL/api/skills/essay-correction" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $INKCRAFT_API_KEY" \
  -H "x-api-key: $INKCRAFT_API_KEY" \
Confidence
97% confidence
Finding
The skill explicitly transmits user essay content and related fields to a third-party endpoint via curl, authenticated with an API key. Even though this is the intended function of the skill, it is still a real external-transmission risk because sensitive educational or personal data may be sent off-platform, and the base URL can be overridden via environment variable, expanding the trust boundary.

Static analysis

No suspicious patterns detected.