ClawHub
Back to skill

Security audit

新闻订阅每日简报

Security checks for vulnerabilities and agentic risk

Overview

The skill’s news-briefing workflow is mostly coherent, but it asks users to use a raw Twitter/X browser session token without adequate safety guidance.

Review before installing. Use a protected environment variable or secret store for TWITTER_AUTH_TOKEN, do not paste the token into chat or commit it to files, and consider whether sending summarized posts and metadata to Feishu/Lark is acceptable for your data policies.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs the agent to read and write local files and potentially access environment-backed credentials, yet it declares no permissions. This creates a trust and containment problem: operators may enable or execute the skill without understanding that it can modify state files and use sensitive runtime data, increasing the chance of unauthorized file changes or credential exposure.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill tells users to obtain a Twitter/X auth_token from browser cookies but does not warn that this is a highly sensitive session credential equivalent to account access. Mishandling, logging, or storing this token insecurely could let an attacker hijack the user's Twitter/X session or abuse the account.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs delivery of collected content through Feishu/Lark without warning that gathered posts, summaries, and metadata are transmitted to an external messaging platform. Users may unknowingly send sensitive or policy-restricted content outside the local environment, creating confidentiality and compliance risk.

Static analysis

No suspicious patterns detected.