Back to skill

Security audit

百度网盘 EVA

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently provides Baidu Netdisk list, search, and directory-creation commands using user-supplied OAuth credentials, with no evidence of hidden persistence, exfiltration, or destructive behavior.

Install this only if you intend to let the skill access your Baidu Netdisk account using your OAuth token. Treat list and search results as private metadata, and confirm mkdir requests yourself because they create remote directories in the account.

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
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description says it manages Baidu Netdisk files but does not clearly warn users that it will access their cloud account and perform remote operations such as listing, searching, or creating directories. This lack of transparent disclosure increases the risk of users authorizing or invoking account-affecting actions without understanding the data-access scope or consequences.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger conditions include broad everyday terms like '网盘' and generic file-management phrases, which can cause the skill to activate in contexts the user did not intend. Because this skill performs remote cloud-drive operations, accidental invocation could expose file listings or initiate management actions against a real Baidu Netdisk account.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The create_dir function performs a write operation against the Baidu Netdisk API, which changes user data by creating a directory. Although the command name implies creation, there is no confirmation prompt, explicit warning, or user-facing disclosure beyond the success message after the action has already occurred.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The module description, help text, and user-facing messages are consistently presented in Chinese, which imposes a specific language on users. There is no indication that the skill is region-specific or that users can opt into another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest presents all user-facing descriptions and keywords in Chinese, with no indication that language selection is optional or that the skill is intentionally limited to Chinese-speaking users. This can violate language or locale policy when a skill appears to enforce a specific language without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This manifest defines commands like listing, searching, and creating directories, but it does not specify any trigger scope, exclusion conditions, or negative examples. In a manifest file, such broad command descriptions can make invocation conditions ambiguous, especially for common actions like 'list' or 'search'.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.