ClawHub
Back to skill

Security audit

huo15-detective

Security checks for vulnerabilities and agentic risk

Overview

This is a review-needed investigative skill because it guides personal background checks, including partial ID and risk-record lookup, without privacy or authorization limits.

Install only if you will use it for legitimate, authorized due diligence. Avoid using it to investigate private individuals unless you have a lawful basis and consent or another clear authorization, and minimize collection of identifiers such as partial ID numbers.

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 (2)

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill explicitly covers personal background investigation and advises checking partial ID information, employment history, related companies, and risk records, yet it provides no privacy, consent, lawful-basis, or data-minimization warning. This makes the skill materially more dangerous because it operationalizes the collection and reporting of sensitive personal information in a way that could facilitate doxxing, invasive surveillance, or non-compliant processing of personal data.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger section includes broad phrases such as '背景调查' and '查公司信息', which can overlap with ordinary user requests and cause the skill to auto-activate unexpectedly. In a skill that performs investigative workflows and recommends collecting sensitive business or personal data, unintended activation increases the chance of unnecessary data gathering, privacy-invasive behavior, or the model steering into a high-risk process without clear user intent.

Static analysis

No suspicious patterns detected.