Back to skill

Security audit

Baidu Baike Data 1.1.0

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Baidu Baike lookup helper that uses a Baidu API key to query encyclopedia entries and print results.

Install this only if you intend to use Baidu Baike as the source and are comfortable providing a BAIDU_API_KEY. Search terms and the API key are sent to Baidu's AppBuilder Baike API when the script runs.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

The documented behavior understates the skill’s real capabilities and dependencies, including lookup by internal ID, candidate enumeration, credential use, and outbound API access. When a skill’s description does not accurately reflect what it does, reviewers and users may grant it trust or execution in contexts they would otherwise restrict, which can enable data handling or network behavior outside expected bounds.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
79% confidence
Finding

The README presents the skill exclusively as a Baidu Baike query tool and gives no indication that users can choose another language or encyclopedia source. Because Baidu Baike is a Chinese-language, locale-specific knowledge source, this can amount to a language/locale constraint that is not explicitly offered as an opt-in or justified as region-specific.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill declares environment-variable and network-dependent behavior but does not define an explicit tool/permission scope. This creates a transparency and policy-enforcement gap: a caller or platform may not realize the skill can access credentials and perform outbound requests, increasing the risk of unintended secret exposure or unauthorized network use.

Content

No source excerpt is available for this finding.