Security audit

公众号热门文章查询

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent WeChat article trend search tool with disclosed Redfox API use, API-key configuration, optional HTML output, and a user-confirmed recurring subscription feature.

Install only if you are comfortable sending WeChat search keywords and date ranges to Redfox using your REDFOX_API_KEY. Treat the subscription option as creating an ongoing calendar reminder, and check how to cancel it before relying on recurring pushes.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 97% confidence
Finding: The skill declares no permissions, but its documentation clearly instructs use of environment variables, network access to an external API, and HTML file generation. This creates a transparency and policy gap: users and hosting platforms cannot accurately evaluate what the skill can access or persist, increasing the chance of unintended data exposure or unauthorized side effects.

Context-Inappropriate Capability

Medium

Confidence: 95% confidence
Finding: The skill is presented as a search tool, but it mandates creation of recurring calendar subscription tasks and says this step cannot be skipped. Persistent actions like scheduled reminders outlive the immediate user request and can cause unwanted notifications, retention of search terms, and privilege escalation into another tool domain without strong purpose limitation.

Vague Triggers

Medium

Confidence: 85% confidence
Finding: The trigger description is broad enough to overlap with common requests for inspiration, article search, or trend discovery. Over-broad activation increases the chance the agent invokes external networked behavior and file-producing workflows when the user did not specifically intend to use this skill.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill advertises timed subscription/push behavior but does not prominently warn users that this creates an ongoing recurring action with future notifications and retained search parameters. In context, this is more dangerous because the subscription is framed as part of normal usage, which can normalize consent to persistence beyond a one-time search.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The document instructs use of an X-API-Key for an external request and also documents a debug mode that prints raw API responses, but it does not warn against exposing secrets or sensitive response contents in logs, examples, or shared output. In a skill context, this can lead to accidental credential leakage, disclosure of upstream data, and easier misuse of the external API by anyone who obtains the key.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: references/gzh_trend_data_format.md:20