ClawHub
Back to skill

Security audit

baidu baike search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Baidu Baike lookup helper that uses a disclosed API key and fixed Baidu endpoint, with no evidence of hidden persistence, exfiltration, or destructive behavior.

Install only if you are comfortable providing a Baidu API key and sending searched terms to Baidu's AppBuilder Baike service. Keep the API key scoped and avoid querying private or sensitive terms unless that disclosure is acceptable.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding

The code is broadly related to Baidu Baike querying, so the overall domain matches the description. However, the implementation differs in material ways from the declared purpose. The description emphasizes returning a standardized, detailed encyclopedia explanation for a user-provided noun, but the code removes key explanatory fields such as summary, abstract_html, and abstract_structured, making the returned content less like a full entry explanation. It also exposes extra behaviors not mentioned in the description: lookup by lemma ID and a lemmaList mode for listing multiple matching entries for title disambiguation. These are not necessarily harmful, but they are undeclared functional capabilities, so this should be flagged as a mismatch.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill requires environment access to read BAIDU_API_KEY and performs outbound network requests, but it does not declare any explicit tool scope such as permissions or allowed-tools. This weakens policy enforcement and review because operators and calling agents cannot easily constrain what the skill is allowed to access, increasing the risk of unintended secret exposure or uncontrolled external communication.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest describes a knowledge-query tool whose core function is returning Baidu Baike entries for supplied nouns. While network access to Baidu Baike is expected, reading process environment state for credentials is an additional capability not mentioned in the stated scope and is not inherently implied by the user-facing purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.