Security audit

Multi Search Engine 2.0.1

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed search-helper skill that builds third-party search URLs, with privacy and content-safety caveats but no hidden execution, persistence, or credential handling.

Install only if you are comfortable with your search queries being sent to the selected third-party search engine. Do not use it for secrets, credentials, private internal names, sensitive personal data, or searches that would violate law or policy; be cautious with safe-search-off options and dual-use advanced operators.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

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: 89% confidence
Finding: The file presents all descriptive and instructional content in Chinese, including headings, feature descriptions, changelog entries, and usage examples. Under the policy rules, forcing a specific language without user opt-in or a documented justification is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill encourages users to issue searches through multiple third-party search engines but does not warn that search terms will be transmitted to external providers, potentially exposing sensitive queries, internal project names, credentials pasted by mistake, or other private data. In this context, the omission is security-relevant because the skill is specifically designed to route user input to many external domains, including engines with different privacy characteristics and jurisdictions.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This markdown file documents the kp=-1 DuckDuckGo parameter as '关闭安全搜索' and presents it as a normal option, but does not warn that it may expose the user to explicit, unsafe, or otherwise sensitive content. For markdown files, omission of warnings about behaviours affecting user safety or system/data integrity should be flagged when such risky behaviour is described.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The config includes several CN-specific engines and regions, such as Baidu, Bing CN, and other China-focused providers, but provides no indication that users can opt into or out of this locale-specific routing. Under the policy, forcing a specific language or locale without user choice can be a natural-language policy concern even in configuration values.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The privacy advice suggests '使用Tor浏览器 + DuckDuckGo onion服务' for sensitive searches, but does not disclose that Tor usage may be restricted by some organizations or jurisdictions and can trigger monitoring or access limitations. In a markdown skill guide, recommending privacy-impacting network behaviour without contextual warning can leave users unaware of relevant risks.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.