Security audit

26 Multi Search Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only search helper that points agents to user-chosen search engines, with privacy and locale caveats but no hidden code or persistence.

Install only if you want an agent to perform web searches through the listed third-party search engines. Do not use it with secrets, credentials, personal data, confidential investigation terms, or internal identifiers unless you are comfortable sending those queries to the selected provider. Review the CN/global engine choice for your locale and privacy needs.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (7)

Ae1

High

Category: analysis-evasion
Content: - `references/international-search.md` - International search guide
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: This markdown file contains user-facing operational descriptions entirely in Chinese, including headings, feature descriptions, and usage context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicit and justified, which is not present here.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill encourages direct web_fetch calls to third-party search engines using raw user queries but does not disclose that those queries will be transmitted to external providers. This creates a privacy and data-handling risk because sensitive user inputs, internal topics, or investigative terms may be exposed to search engines with different logging, tracking, and jurisdictional practices.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The Bing entries explicitly force the cn.bing.com domain and use parameters tied to Chinese search behavior, which imposes a specific locale/market configuration in the skill data. This is a natural-language policy concern because the file provides no opt-in, alternative selection mechanism, or justification for forcing that locale.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The document includes many `web_fetch` examples that send user-supplied queries directly to third-party search engines, but it does not warn that search terms, IP metadata, and browsing context may be disclosed externally. In a skill intended for automated agent use, this omission can lead users or downstream developers to unknowingly exfiltrate sensitive prompts, research topics, or internal identifiers to external services.

Natural-Language Policy Violations

Low

Confidence: 82% confidence
Finding: The skill mixes CN-focused and global search engines without documenting how locale selection should occur or warning that different providers may route queries to different regions and legal regimes. In context, this increases the chance that users unknowingly send searches to region-specific services with different censorship, logging, privacy, and compliance characteristics.

Natural-Language Policy Violations

Low

Confidence: 86% confidence
Finding: The document is entirely written in Chinese and does not indicate that the user can choose another language or that the Chinese-only presentation is a justified regional constraint. The policy requires flagging language or locale restrictions when they are imposed without user opt-in or clear justification.

Static analysis

No suspicious patterns detected.