Back to skill

Security audit

Ultimate Search Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward search-helper skill that sends user-selected queries to external search engines and shows no hidden code, persistence, or local data access.

Before installing, be aware that search terms may be sent to whichever external engine the agent uses, and those providers may log or process queries under their own policies. Avoid putting secrets, private project names, personal data, or credentials into search queries, and use the advanced search examples responsibly.

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
  • 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 (6)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 105)May include surrounding context.

md
- `references/international-search.md` - International search guide

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file presents core headings, descriptions, and usage information only in Chinese, which effectively forces a specific language for understanding and use. The policy allows language constraints only when users are given a choice or when the locale restriction is explicitly documented and justified, neither of which appears here.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documents direct requests to many third-party search engines and encourages passing raw user queries in URL parameters, but it does not warn that those queries will be transmitted to external services with their own logging, tracking, and jurisdictional privacy practices. In a search aggregation skill, users may submit sensitive prompts, internal project names, or personal data, so silent disclosure to multiple providers creates a real privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file presents all instructional content in Chinese from the title onward, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. That creates a natural-language policy concern because it effectively forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The description and engine list explicitly prioritize both 'CN' and 'Global' search engines, including region-specific endpoints such as Bing CN and Google HK, but the documentation does not state how locale is selected or provide user opt-in for region-specific behavior. This can create an implicit locale policy issue because the skill appears to steer search behavior by region without documented user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This manifest includes multiple CN-specific engines and region values such as "cn" and a China-specific Bing endpoint, which imposes locale-specific behavior in configuration without any visible indication of user opt-in or alternative selection logic in this file. Under the policy rule for natural-language locale violations, hard-coded locale constraints can be problematic when they are not clearly justified or presented as a user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.