Security audit

市场洞察师

Security checks for vulnerabilities and agentic risk

Overview

The skill is a market-research helper, but it includes guidance about proxies, cookies, and bypassing anti-scraping controls that users should review before installing.

Install only if you are comfortable enforcing your own guardrails: use public data or official APIs, do not use proxy rotation, borrowed cookies, shared sessions, or login bypasses, and restrict any collector run to approved domains and local output folders.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (8)

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The document claims to recommend legal collection methods, but later includes operational guidance suggesting anti-scraping protections are 'bypassable' or require cookies/proxy pools. In a market-intelligence skill whose purpose includes competitor monitoring and data collection, this materially lowers the barrier to unauthorized scraping and can encourage Terms-of-Service violations or circumvention of access controls.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The text explicitly provides guidance about anti-scraping difficulty and mentions methods such as proxy pools, bypassing anti-crawling controls, and using cookies for access. Even without executable code, this is actionable operational advice that can facilitate unauthorized collection, evasion of platform defenses, and potentially unlawful access behavior.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 94% confidence
Finding: The skill describes capabilities that imply network access and filesystem writes, including fetching platform data and storing outputs under local directories, but it does not declare any explicit tool scope or permission boundaries. This creates an authorization gap where a host agent may invoke broader-than-necessary tools, increasing the risk of unintended data access, excessive scraping, or arbitrary file writes if the skill is activated in the wrong context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The activation description is very broad, covering market analysis, policy tracking, competitor monitoring, reporting, and opportunity identification across many platforms without clear trigger constraints. Overbroad routing can cause this skill to be invoked for loosely related tasks, which is dangerous here because the skill also contemplates network collection and file persistence, expanding operational reach beyond what a user may have intended.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The scheduled workflow is fixed to Beijing time (北京时间), which imposes a locale-specific operating assumption in the skill documentation. The file does not indicate that timezone selection is configurable or based on user preference, creating a locale policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The entire skill file is written only in Chinese and does not indicate that language selection is optional or that the skill is explicitly limited to Chinese-speaking users. Under the policy, a skill that forces a specific language without user opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 78% confidence
Finding: L278-L280 明确声明禁止“绕过登录获取付费数据”，但前文多处又把“作者后台：需登录获取详细数据”作为数据来源说明。这种写法容易混淆“合法登录访问自有后台数据”和“绕过登录获取他人或付费数据”的边界，导致文档意图不清并形成实际指导上的矛盾。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This code file contains natural-language instructions and usage text only in Chinese, including the module docstring and CLI descriptions. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.