Alicloud Backup Bdrc

• Outcome: Pass
• Latest audit: May 28, 2026 at 11:43 AM UTC
• Version:
  1.0.3

Overview

This is a disclosed Alibaba Cloud BDRC management helper with expected credential use, API access, and local output files for that purpose.

Install this only if you want an agent to help manage Alibaba Cloud BDRC. Use a dedicated least-privilege AccessKey, verify the account, region, and resource IDs before use, approve any Create/Update/Modify/Set action explicitly, and review or delete files in output/alicloud-backup-bdrc/ before sharing the workspace.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 88% confidence
• Finding: The skill explicitly relies on environment variables for cloud credentials, writes artifacts to disk, and uses network access to query Alibaba Cloud/OpenAPI metadata, yet it declares no permissions. That gap prevents informed consent and weakens sandboxing or policy enforcement, especially because the skill can access secrets and persist potentially sensitive cloud data.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 84% confidence
• Finding: The documented purpose is managing BDRC resources, but the described behavior includes metadata enumeration and local artifact generation that are not clearly disclosed as part of the primary function. This mismatch can mislead operators about what the skill will actually do, increasing the chance of unreviewed network calls and collection/storage of cloud API inventory data.

Missing User Warnings

Medium

• Confidence: 81% confidence
• Finding: The skill supports mutating backup and disaster-recovery operations such as create, update, modify, and set actions, but it does not prominently warn about the operational risk of changing backup policies or recovery settings. In a BDRC context, incorrect changes can degrade backup coverage, alter retention, or disrupt recovery posture for production systems.

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The skill instructs saving API responses, command outputs, and evidence files without warning that these artifacts may contain sensitive cloud metadata such as resource IDs, regions, account structure, timestamps, and possibly operational status details. Persisting that data locally increases exposure through logs, shared workspaces, or later exfiltration.

VirusTotal

66/66 vendors flagged this skill as clean.