ClawHub
Back to skill

Security audit

翱象发品

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent guide for batch publishing retail products, but it deserves review because it can change a merchant account at scale and uses API secrets without clear safety controls.

Review this before installing if the connected merchant account is real. Use least-privilege credentials, keep secrets in environment variables or a secret manager, test with non-production merchant/store codes first, and require explicit approval before any batch publish run.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly supports bulk creation/publishing of goods to an external retail platform, but the description does not warn users that invoking it can cause real external state changes at scale. In an agent setting, missing an execution-impact warning increases the chance of accidental or unauthorized bulk publication, which can create operational, financial, or reputational harm.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The documentation instructs users to supply an app key and secret but does not include any warning about secure credential handling, storage, or logging. In agent workflows, this can lead to secrets being pasted into prompts, committed to files, or exposed in logs, enabling unauthorized API use against the merchant account.

Static analysis

No suspicious patterns detected.