Security audit

multi-search-engine

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward search-engine reference that tells the agent how to query public search providers, with privacy and locale considerations users should understand before use.

Install only if you are comfortable with your search terms being sent to the selected external search engine. Avoid putting secrets, personal data, internal project names, or confidential research terms in queries, and prefer a privacy-oriented provider when searches are sensitive. Treat the package's privacy claims as guidance, not guarantees.

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
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

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The examples instruct use of web_fetch against third-party search engines without warning that user queries will be transmitted to external services. In a search-integration skill, this can expose sensitive prompts, identifiers, or internal research terms to outside providers, especially because the feature explicitly encourages broad multi-engine querying.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill instructs users to issue web requests to multiple third-party search engines, but it does not clearly warn that user queries will be transmitted to external services. Search terms can contain sensitive research topics, internal project names, credentials accidentally pasted by users, or personal data, creating a meaningful privacy and data-exposure risk. The skill context increases the risk because its whole purpose is sending arbitrary user-provided queries to many external domains, including privacy-varying and cross-jurisdiction providers.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This manifest contains multiple search providers explicitly labeled with the cn region, including Bing CN, and does not indicate any user-selectable locale behavior. Because the policy applies to all file types, hard-coding locale-specific behavior without opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This markdown guidance forces a specific language/locale for the skill content, and there is no indication that users may opt into another language or receive alternatives. The policy explicitly calls for flagging language or locale constraints when they are imposed without user choice or clear justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: Most of the skill documentation, including headings and feature descriptions, is presented only in Chinese. If organizational policy requires avoiding forced language/locale constraints, this can be a natural-language policy issue because no opt-in, alternative language, or explicit region-specific justification is provided.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The skill presents a China-oriented engine set and labels domestic engines prominently without any user opt-in, locale selection guidance, or explanation of regional implications. While not a direct exploit primitive, this can route user searches to region-specific providers with different censorship, monitoring, privacy, or legal characteristics than the user expects. The danger is somewhat moderated by the fact that international engines are also listed, but the documentation still nudges usage toward a specific locale context without explicit consent.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.