360 Search

• Outcome: Pass
• Latest audit: Sep 12, 2026 · 12:36 AM UTC
• Version: 1.0.3

Overview

This is a straightforward 360 Search helper that sends user search terms to so.com, with some documentation and packaging rough edges but no hidden or destructive behavior found.

Install only if you are comfortable sending search queries to 360 Search/so.com. Expect Chinese-only output and some packaging issues, such as missing or inconsistent example files, but the inspected artifacts do not show hidden persistence, credential access, or destructive actions.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (10)

Natural-Language Policy Violations

Medium

• Confidence: 88% confidence
• Finding: Natural-language strings in the file, including the module description and runtime messages, are primarily in Chinese, which can impose a language choice on users without opt-in. The file does not document that this skill is intentionally limited to a Chinese-speaking or region-specific context.

Missing User Warnings

Low

• Confidence: 91% confidence
• Finding: This code sends the user-provided query to https://www.so.com via a browser navigation request, which is a network operation that transmits user data to a third party. While the file describes that it performs web search, it does not include any explicit warning, confirmation, or disclosure that user-entered queries will be sent externally.

Missing User Warnings

Low

• Confidence: 90% confidence
• Finding: The news search method constructs a remote so.com URL using the supplied query and loads it in Playwright, transmitting the query to an external provider. The method lacks any explicit user disclosure or warning about this data transfer.

Missing User Warnings

Low

• Confidence: 90% confidence
• Finding: This method issues a network request to so.com with the user's image-search query embedded in the URL. There is no explicit warning in comments, docstrings, or user-facing output that the query will be transmitted to a third-party search engine.

Natural-Language Policy Violations

Low

• Confidence: 88% confidence
• Finding: SQP-3 applies to all file types and includes language or locale policy issues. The visible natural-language documentation is entirely in Chinese, and the file does not indicate that this language choice is optional, user-selectable, or justified by a region-specific constraint.

Missing User Warnings

Low

• Confidence: 77% confidence
• Finding: This is a markdown file, so SQP-2 applies to omissions in user-facing safety disclosures. The documentation tells users to check `.env.example` for required environment variables but provides no warning about whether those variables may include API keys or other sensitive data, which is relevant for a search skill that likely interacts with external services.

Missing User Warnings

Low

• Confidence: 81% confidence
• Finding: This Python file performs an image search via `client.search_image(...)`, which implies a network/HTTP request transmitting the user-provided query to an external service. The script has no confirmation prompt, user-facing disclosure, or explanatory comment/docstring warning that the query will be sent out, so users invoking the script from code alone are not informed of that data transmission.

Natural-Language Policy Violations

Low

• Confidence: 94% confidence
• Finding: The docstring and usage message are written only in Chinese, which imposes a specific language on users without any opt-in or alternative. Under the stated policy, forcing a language or locale without user choice is a natural-language policy violation.

Missing User Warnings

Low

• Confidence: 80% confidence
• Finding: This Python file creates a Search360Client and performs a news search, which likely issues network requests based on user-supplied query data. The script provides usage text but no explicit warning, log, or comment disclosing that the query will be transmitted to an external search service.

Natural-Language Policy Violations

Low

• Confidence: 90% confidence
• Finding: The file’s docstring and all user-facing messages are in Chinese, including status output and assertion text. This imposes a specific language/locale without any opt-in or indication that the skill is intentionally region-specific, which matches the natural-language locale policy concern.

Static analysis

No suspicious patterns detected.