ClawHub
Back to skill

Security audit

企业触达路径挖掘

Security checks for vulnerabilities and agentic risk

Overview

This skill is a public-information business outreach research workflow with clear compliance limits and no evidence of hidden execution, persistence, or private data access.

Install only if you want a Chinese-language workflow for compliant enterprise outreach research. Users should keep outputs limited to official/public channels, verify all contacts before use, and avoid using it for personal contact discovery, impersonation, pressure campaigns, or bypassing an organization's formal intake paths.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The activation description is extremely broad and can match many ordinary enterprise research, business development, or government-relations requests without strong gating. In this skill’s context, that matters because the skill generates detailed contact-path and outreach strategies, so over-activation could steer benign user queries into high-risk lead-mining and persuasion workflows that facilitate targeted influence or unwanted solicitation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list contains broad phrases like contact channel lookup, contact clue organization, and customized outreach scripting, which overlap with normal business-information requests and can be invoked too easily. Because this skill is specifically optimized to identify reachable paths, key roles, and persuasive entry points, ambiguous triggers increase the chance of inappropriate activation for social-engineering-adjacent targeting or evasive outreach planning, even though the text includes compliance language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description and all trigger phrases are written only in Chinese, which indicates the skill is designed to activate and operate in a single language. There is no accompanying note that the skill is China-specific or that users may opt into another language, creating a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.