ClawHub
Back to skill

Security audit

Alibaba Cloud OSS

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for managing Alibaba Cloud OSS, but it needs review because its setup guidance can execute remote installer scripts and its cloud-storage authority includes destructive operations.

Review before installing. Use this only with an OOMOL and Alibaba Cloud OSS account you intend the agent to operate, manually verify or install the oo CLI through trusted documentation instead of blindly running the pasted installer commands, and require confirmation for uploads, deletes, overwrites, and presigned URLs that grant write or delete access.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into a shell, which is a classic arbitrary code execution pattern. If the remote host, delivery path, or script content is compromised, running this command would execute attacker-controlled code on the system with the user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description says to use this skill for "ANY Alibaba Cloud OSS request" and "Whenever a task involves Alibaba Cloud OSS, use this skill," which is extremely broad and does not define clear boundaries or exclusions. This can cause unintended invocation for casual mentions or tasks where direct API use or another tool might be more appropriate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.