ClawHub
Back to skill

Security audit

Sjtu

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only guide for using an SJTU Discourse forum, with no executable code or hidden agent behavior.

Installers should understand this skill is an informational forum guide. When using the actual Shuiyuan site, review its cookie/privacy settings before logging in or posting, especially because the guide notes analytics, device identifiers, and session cookies.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file describes cookies, device fingerprint identifiers, analytics, storage mechanisms, and background services such as push messaging and reporting APIs, but does not warn users that using the site may involve tracking or persistent identifiers. Under the markdown-specific missing-warning rule, privacy-affecting behaviours should be disclosed with an explicit caution or note.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.