ClawHub
Back to skill

Security audit

Daily Digest

Security checks for vulnerabilities and agentic risk

Overview

This skill locally summarizes Markdown files and shows no hidden network, credential, persistence, or destructive behavior.

Install only if you are comfortable with the agent reading Markdown files in the current or specified folder and printing document metadata. In sensitive workspaces, invoke it with an explicit narrow directory rather than from a project root.

SkillSpector

Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill clearly instructs scanning the current working directory or a user-supplied directory for all .md files, which is a file-read capability, but no permissions are declared. This creates a transparency and least-privilege problem: the agent may read local documents without an explicit permission contract, increasing the chance of overbroad data exposure if invoked in a sensitive workspace.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrases are broad, everyday requests such as '生成今日摘要' and 'daily digest', which could match normal conversation and cause unintended skill activation. In this skill's context, accidental invocation is more concerning because activation leads to enumerating and reading markdown files in the workspace, potentially exposing document metadata or contents without the user explicitly asking for file access.

Static analysis

No suspicious patterns detected.