ClawHub
Back to skill

Security audit

AIGC Detection

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to perform the stated AI-detection function, but it uploads user content to a remote service and persistently stores account tokens locally without clear opt-in or removal guidance.

Before installing, understand that detection content and uploaded files are sent to the 睿小鉴 backend, and login uses a phone/SMS flow that stores bearer and refresh tokens in a local file. Avoid submitting sensitive files unless you are comfortable with that service processing them, and remove ~/.ruijian-token.json or revoke access if you stop using the skill.

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 explicitly instructs storing access and refresh tokens in a local file under the user's home directory, but does not require clear user consent, explain persistence risks, or prefer a secure secret store. Persisted bearer and refresh tokens can be stolen by other local processes, backups, or accidental disclosure, enabling unauthorized account access and API use until revoked or rotated.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill routes user text, images, audio/video, and documents to a remote backend HTTP API for analysis, but the description does not clearly warn users that their content will be transmitted off-platform. This creates a privacy and consent issue, especially because uploaded files may contain sensitive personal, business, or regulated data that users may not expect to leave the local environment.

Static analysis

No suspicious patterns detected.