ClawHub
Back to skill

Security audit

AI资讯网站生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill generates a local RSS news website and its risks are mostly expected for that purpose, with deployment and feed-source cautions users should understand.

Install only if you want a generated RSS aggregation web app. Review the generated files before running Docker, pip, or npm; use a new empty target directory; validate RSS feed URLs; and add authentication, restricted CORS, localhost binding or firewall rules, and other hardening before exposing it publicly.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill clearly instructs users to run a local generator script, create project files, use Docker Compose, and fetch external RSS feeds, which implies shell execution, file writes, and network access. Because these capabilities are not explicitly declared, users and any policy layer may underestimate the operational and security exposure, including executing unreviewed local code and deploying services that reach out to external endpoints.

Missing User Warnings

Low
Confidence
77% confidence
Finding
The skill promotes one-click deployment of an RSS aggregation website but does not clearly warn that the generated backend will continuously fetch from configured RSS URLs and may expose aggregated content over localhost or publicly reachable services if deployed. This omission can lead users to deploy a network-facing content proxy/aggregator without understanding SSRF-adjacent feed risks, legal/content exposure, or the consequences of publishing fetched material.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
templates/frontend-page.tsx:26