Security audit

Multi Search Engine

Security checks for vulnerabilities and agentic risk

Overview

This is mostly a search-helper skill, but it includes unscoped examples for finding potentially sensitive password and admin-login pages.

Review this skill before installing if you expect a strictly safe general-search assistant. It does not install code or request credentials, but users should avoid using its advanced search patterns to look for exposed passwords, admin pages, private files, or other sensitive third-party data without authorization.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

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 uses Chinese for its headings and descriptive content, which effectively forces a specific language for understanding and use. Under the policy, locale or language constraints should be optional or explicitly justified, but no opt-in or justification is provided here.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: The document title and all instructional content are presented solely in Chinese, establishing a fixed language for the skill with no indication that users may choose another language. This is a natural-language locale policy concern because the file does not offer opt-in or alternative language handling.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: The config defines multiple engines explicitly labeled with region "cn" and includes locale-specific behavior such as the Bing CN endpoint with ensearch parameters. Because the file provides only fixed locale-targeted options and no natural-language indication of user opt-in or choice, it may conflict with the policy against forcing a specific language/locale without user consent.

Static analysis

No suspicious patterns detected.