ClawHub
Back to skill

Security audit

Alibaba Cloud AI Search Rerank

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed helper for preparing Alibaba Cloud rerank request JSON and does not show hidden, destructive, credential, network, or persistence behavior.

Before installing, note that using the helper will create local output files and that the --output option can write wherever the running agent has permission. It does not itself contact Alibaba Cloud or use credentials, so actual API calls and credential handling would happen outside this skill.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill performs file-writing during validation and normal usage (output/.../validate.txt and request.json) but does not declare any tool scope such as permissions or allowed-tools. This creates an authorization gap: environments that rely on manifest-declared capabilities may permit undeclared filesystem side effects, reducing transparency and policy enforcement.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.