ClawHub
Back to skill

Security audit

「拾句」金句语录

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently fetches and formats public quote content, with optional image-card generation, and I found no hidden persistence, credential access, destructive behavior, or deceptive instructions.

Before installing, expect the skill to contact tuyulu.com for public quote data and to use image/file tools when you ask for a daily quote card. Review generated quotations and attributions before publishing them publicly, especially when the skill marks an origin as uncertain.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill invokes network access and file-producing behaviors (`fetch_quote.py`, `web_fetch`, `present_files`) but does not declare any tool scope or permission boundaries. That creates an authorization and governance gap: an agent may use broader-than-necessary capabilities, increasing the risk of unintended external requests, data exfiltration, or file writes beyond the user’s expectation.

Vague Triggers

Medium
Confidence
90% confidence
Finding
This is a markdown file, so vague-trigger review applies. The example triggers are common conversational requests that could overlap with ordinary chat and the file does not provide exclusion conditions or tighter activation boundaries, increasing the risk of unintended invocation.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The instructions require Chinese branding and Chinese quotation marks, and the overall skill is written as if output should be in Chinese only. Because the file does not offer a user opt-in or explain that the skill is intentionally Chinese-only for a specific regional use case, this is a natural-language locale policy concern.

Static analysis

No suspicious patterns detected.