Baidunetdisk Skill

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill appears purpose-aligned for Baidu Netdisk file management, but it requires full-access Baidu session credentials and can perform irreversible file changes.

Install only if you trust the environment and are comfortable giving the skill full Baidu Netdisk access. Store BDUSS/STOKEN securely, avoid shared machines, verify paths before move/rename/delete, and consider using a separate Baidu account for testing.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If these credentials leak or are misused, someone could access or change files in the Baidu Netdisk account.

Why it was flagged

The skill requires Baidu session credentials with full access to the user's Netdisk account. This is disclosed and purpose-aligned, but it is high-impact credential use.

Skill content
本 Skill 需要您的百度网盘登录凭证(BDUSS 和 STOKEN),这些凭证具有完全访问您网盘账户的权限
Recommendation

Use a test or low-risk account if possible, prefer environment variables or protected config files, restrict file permissions, and revoke/refresh credentials when done.

What this means

A mistaken or overbroad delete path could remove cloud files from the user's Baidu Netdisk account.

Why it was flagged

The provided code can call Baidu's filemanager delete API for a user-supplied path. This matches the file-management purpose, but it is destructive.

Skill content
def delete_file(self, path: str): ... url = "https://pan.baidu.com/api/filemanager" ... 'opera': 'delete' ... 'filelist': json.dumps([path])
Recommendation

Only invoke delete, move, or rename with explicit user intent; verify exact paths before running; consider adding an extra confirmation step for destructive operations.

What this means

Installing unpinned dependencies can make environments less reproducible and can expose users to dependency changes over time.

Why it was flagged

Setup uses manual, unpinned Python package installation. This is normal for a small API client, but it leaves dependency version/provenance control to the user.

Skill content
pip install requests tqdm
Recommendation

Install in a virtual environment, use trusted package indexes, and pin dependency versions if deploying in a sensitive environment.