ClawHub
Back to skill

Security audit

Daojia

Security checks for vulnerabilities and agentic risk

Overview

This skill is a lightweight JD Daojia public-page analysis guide with no executable code, persistence, credential handling, or hidden behavior.

Install only if you want an agent to help summarize publicly visible JD Daojia merchant or product pages. Avoid using it for account actions, ordering, scraping at scale, or attempts to bypass platform controls; those are outside the skill's stated boundaries.

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 activation text is broad enough to trigger on many generic requests involving JD Daojia access or automation, which can cause the agent to invoke this skill in situations beyond narrow public-page summarization. Over-broad routing increases the chance of unnecessary browsing or collection against a third-party site and can bypass safer, more specific skills or user-intent checks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.