Security audit

Multi-Search Fallback

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only search aggregation skill whose broad routing may over-activate but whose behavior is disclosed and aligned with its purpose.

Install this if you want automatic multi-source search and result comparison. Be aware that broad search-like prompts may trigger it and may send your query to multiple search providers, so avoid using it for private or sensitive queries unless you are comfortable with that exposure.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (4)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger pattern is extremely broad (e.g., 搜索|查|研究|验证 and generic English terms), which can cause this skill to activate for many ordinary requests that merely mention checking, researching, or comparing something. Because the skill also states that all search-like needs should prioritize this skill, it can hijack normal routing, over-invoke tools, and expand data exposure or unintended external queries beyond user intent.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description is written in Chinese and presents the skill behavior/output expectations in that language, with no indication that users may choose another language or that the skill is region-specific. Under the policy, forcing a specific language without opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill description is written to impose a fixed behavior and prioritization model without clear user opt-in, and the finding indicates language-forcing behavior in that same area. In practice, forcing presentation or workflow style without respecting user preference can degrade reliability, cause inappropriate activation contexts, and make the agent less aligned with user expectations, especially in multilingual environments.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The manifest description is written entirely in Chinese, which imposes a specific language context without any indication that users can opt into another language or that the skill is intentionally region-specific. Under the policy, forcing a specific language without user choice is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.