Back to skill

Security audit

网页爬取工具

Security checks for vulnerabilities and agentic risk

Overview

This skill needs Review because it mixes Discord DM archiving with generic web scraping and SEO instructions without clear boundaries or consent controls.

Install only after the publisher narrows the skill to one clear purpose, removes unrelated SEO/web-scraping claims, and adds explicit authorization and privacy rules for Discord DMs and credentials. There is no evidence of malicious code in the submitted artifact, but its scope and sensitive-data handling are too ambiguous for ordinary installation without review.

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Intent-Code Divergence

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is internally inconsistent, presenting itself as a Discord archive/DM search tool while also advertising generic web scraping and SEO optimization use cases. This mismatch can mislead users and agents into applying the skill to broader data collection tasks than intended, increasing the risk of privacy-invasive use and unsafe automation decisions.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The documented JSON output is a generic grading/report schema that does not match the claimed Discord archive/search functionality. In security-sensitive automation, schema mismatches can cause downstream agents or users to mis-handle results, ignore missing message data, or make unsafe assumptions about what was actually retrieved.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
93% confidence
Finding

An overly broad invocation phrase tied to generic SEO work encourages the skill to be triggered in contexts unrelated to Discord archiving. Overbroad routing increases the chance an agent will use a tool with exec/read capabilities on inappropriate tasks, leading to data overcollection, privacy issues, or misuse beyond user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill references Discord DMs and archived messages without a prominent warning about consent, privacy, retention, and legal sensitivity. Because DMs can contain highly sensitive personal content, the absence of strong warnings and guardrails increases the chance of unauthorized collection, review, or retention of private communications.

Content

No source excerpt is available for this finding.