Baidu Netdisk

• Outcome: Review
• Latest audit: Nov 4, 2026 · 5:50 AM UTC
• Version: 1.0.7

Overview

This Baidu Netdisk helper needs review because setup executes unverified remote code and downloads copy files to intermediary storage without clear transfer approval.

Approve CLI installation separately after reviewing its source, version, and effects on installed agent skills. Before downloading sensitive files, explicitly authorize the connector-storage copy and establish who can access it and when it is deleted. Keep the existing confirmation requirements for writes, sharing, and moves. The installer and hosted service implementations were not verified; the concerns support Review, not a finding of malicious intent.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Output Handling: Unvalidated Output Injection, Cross-Context Output, Unbounded Output
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 94% confidence

Finding

The visible code performs remote installer execution rather than the declared Netdisk data operations. Although installation can be a supporting implementation detail, this chunk establishes no connection between the installer and Baidu Netdisk functionality. The downloaded script's contents and effects are not available, so no specific downstream behavior or malicious intent can be inferred.

Content

No source excerpt is available for this finding.

External Script Fetching

High

• Category: Supply Chain
• Confidence: 98% confidence

Finding

Piping a mutable HTTPS installer directly into bash executes its contents without prior review or independent integrity verification. Compromise of the distribution endpoint or release process could therefore result in local code execution and access to files or credentials available to the invoking user; the conditional setup trigger reduces exposure but does not eliminate this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

• oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):

  bash

  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
  

  powershell

The safety guidance classifies an action that uploads file contents to transit storage as a read safe to run without confirmation.

Medium

• Category: Excessive Agency
• Confidence: 97% confidence

Finding

The untagged download_file action explicitly uploads file contents to connector transit storage, yet the safety rules classify untagged actions as reads safe to run directly. This conflates leaving the source unchanged with avoiding disclosure, potentially allowing sensitive Netdisk contents to cross a storage trust boundary without informed authorization.

Content

No source excerpt is available for this finding.

The setup workflow executes remotely downloaded installation scripts without warning the user about the system-integrity implications.

Medium

• Category: Output Handling
• Confidence: 94% confidence

Finding

The missing-CLI fallback instructs execution of remotely supplied shell or PowerShell code without explicit approval for local software installation or an integrity-verification step. Although this is a legitimate dependency setup path, it extends a cloud-file task into local code execution with the executing user's privileges.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 80% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 88)May include surrounding context.

md

- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources