ClawHub
Back to skill

Security audit

中国活动预算逐项DD

Security checks for vulnerabilities and agentic risk

Overview

This is a document-only budgeting review skill with clear scope and privacy guardrails, though users should be careful when providing sensitive budget files.

Before installing, users should understand that this skill is meant to analyze sensitive business budget and vendor quote materials. Provide only documents you intend the agent to review, and sanitize confidential details before asking it to use public web searches for benchmarks.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (1)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The default prompt invokes the skill with a very broad phrase and no clear input or trigger constraints, which can cause the skill to be applied in unintended contexts whenever a user asks to review a budget. In an agent ecosystem, overly broad invocation increases the chance of accidental activation, mishandling unrelated documents, or producing negotiation guidance on incomplete or inappropriate inputs.

Static analysis

No suspicious patterns detected.