Back to skill

Security audit

opencli-smart-search

Security checks for vulnerabilities and agentic risk

Overview

This is a search-routing skill that is broad and China/English-source oriented, but its behavior is disclosed, purpose-aligned, and not destructive or persistent.

Install this if you want a Chinese-friendly opencli search router and are comfortable with your search terms being sent to selected external providers. Review source choices for sensitive queries, especially social-media, shopping, travel, finance, or job searches.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (11)

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description explicitly elevates this skill for “中文内容,” which biases routing based on language rather than user consent or task fit. In practice, that can silently force Chinese-language search behavior, alter source selection, and cause privacy, relevance, or policy issues when the user did not ask for Chinese-focused handling.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger text is very broad: it says to use this skill whenever the user wants to search, query, find, or research information, with many example domains. That can cause the agent to over-invoke this skill for ordinary requests, crowding out more appropriate skills and unnecessarily routing user activity through external search tooling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

The guidance explicitly routes Chinese-context queries to one source and provides only Chinese-language example formulations in that section, which can amount to a language/locale preference baked into the skill behavior. The file does not state that users may choose another language or opt in to Chinese-specific handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file is entirely written in Chinese and line L49 gives behavioral guidance for handling user requests in Chinese-only phrasing, while also steering English content to specific sites at L14. This creates a language/locale constraint without any explicit user choice or opt-in, which matches the policy category for forced language behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The phrase '中文或英文社区讨论' specifies Chinese or English community discussion as the intended scope, which is a language constraint expressed in natural language. The file does not indicate that this is optional, user-selected, or required for a documented region-specific reason.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations in natural-language content. This markdown file presents all instructions and routing guidance only in Chinese, with no opt-in, alternative language, or explanation that the skill is region-specific.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The routing rule uses broad terms like “旅行/目的地/景区” and instructs the agent to proactively select tools, which can cause the skill to trigger even when the user did not clearly request travel-site querying. That can lead to unintended external lookups, reduced user control, and misrouting of queries to travel-specific or Chinese-search sources.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The instruction to first use a Chinese-context source (doubao) when the user only mentions generic travel concepts imposes a language and source bias without user opt-in. This may route user queries into a Chinese-language ecosystem unexpectedly, affecting relevance, privacy expectations, and potentially exposing user intent to an unintended provider.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file contains user-facing instructions only in Chinese, which can constitute a language/locale policy issue when no opt-in or alternative language option is provided. The content does not state that the skill is intended exclusively for Chinese-speaking users or a China-specific context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file uses Chinese throughout for headings, descriptions, and routing guidance, but does not indicate that the skill is intended only for Chinese-speaking users or provide any opt-in language choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The routing guidance tells the agent to use social platforms directly when users ask about social media, but the description does not warn that queries may involve sending user-provided topics or identifiers to external services. For a markdown skill reference that guides use of third-party platforms, a brief disclosure about privacy and external service access is expected.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.