ClawHub
Back to skill

Security audit

企业-高管战略意图分析

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed public-executive research and talking-points assistant with no code, persistence, credential use, or hidden install behavior.

Install only if you want an assistant that researches public executive statements and drafts business outreach or negotiation language. Use it deliberately for named targets, verify citations and dates, and avoid relying on speculative personal inferences or non-public information.

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
  • 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
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger description is broad enough to activate on generic requests about company strategy, executive views, visit preparation, or industry attitudes, rather than a narrowly scoped use case. This can cause the skill to run unexpectedly, perform unnecessary web searches, and generate high-risk persuasive intelligence outputs for targets without clear user intent, increasing the chance of privacy-invasive or manipulative use.

Content

No source excerpt is available for this finding.