Security audit

关键词监控系统

Security checks for vulnerabilities and agentic risk

Overview

The skill’s monitoring and report-pushing purpose is coherent, but its privacy statement conflicts with its disclosed use of Tavily and Feishu third-party services.

Review this skill before installing if your keywords, collected content, or reports may contain sensitive business information. Using Tavily will send search queries externally, and enabling Feishu webhook push will send generated reports to a Feishu group, despite the artifact’s local-only privacy wording.

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The privacy section states that all data is stored locally and will not be uploaded to third parties, but the same document explicitly says the skill uses Tavily API and optionally sends reports to Feishu via webhook. This creates a materially misleading data-handling claim that can cause users to expose monitored keywords, retrieved content, and report data to external services without informed consent.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill claims data is not uploaded to third parties, yet it also says it relies on Tavily API for search and content acquisition, which necessarily involves transmitting queries and possibly related metadata to an external provider. This discrepancy undermines transparency and can mislead users about the privacy implications of using the skill.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The description mentions Feishu webhook configuration but does not clearly warn that monitored content and generated reports are transmitted to a Feishu group. In a monitoring and collection tool, that omission increases the risk of accidental disclosure of sensitive keywords, collected content, or competitive intelligence to external recipients.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill description and readme content are presented entirely in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. This can violate language-choice policy when no opt-in or justification is provided.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.