ClawHub
Back to skill

Security audit

复旦

Security checks for vulnerabilities and agentic risk

Overview

This is a simple informational Fudan University skill with no executable code or sensitive system access.

Safe to install as a lightweight university reference skill. Treat its factual university details as static bundled content and verify current admissions, rankings, and program information from official sources when accuracy matters.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The phrase "Activate this skill to access detailed information about Fudan University" does not specify concrete trigger phrases, invocation boundaries, or exclusion conditions. In a markdown skill description, this ambiguity can lead to unintended invocation because it gives no clear guidance on when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.