T08 · Insecure Dependencies
Warning
- Location
SKILL.md:14- Finding
Unverified External MCP Service Introduces a Mutable Third-Party Trust Boundary
- Content
View full analysis
- Remediation
View remediation
Security audit
lingxiao-market-research
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed market-research helper that connects users to a Lingxiao MCP service, with no evidence of hidden code execution, local data access, persistence, or destructive behavior.
Before installing, understand that your market-research queries, category and country parameters, and network metadata may be sent to Lingxiao's MCP service. Avoid submitting confidential product plans, customer data, credentials, or internal strategy unless you trust that service and its privacy terms. Use client controls or approval prompts where available for MCP tool calls.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
Findings (1)
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 (2)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The invocation description is broad enough to trigger on common market-research, keyword-analysis, and country-evaluation requests without clear scoping constraints. In an agent environment, this can cause over-invocation of the skill, unexpected routing to external MCP-backed tooling, and unnecessary disclosure of user queries or business context to a third-party service.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The skill metadata and content are entirely Chinese-centric and do not state that the assistant should preserve or ask for the user's preferred language. This can lead to unexpected language switching, misunderstood outputs, or incorrect execution when users operate in another language, reducing transparency and increasing the chance of user error in security- or business-relevant decisions.
- Content