ClawHub
Back to skill

Security audit

Mobazha Product Description

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill is purpose-aligned, but it tells agents to publish and bulk-update live marketplace listings without clear review or approval safeguards.

Review before installing if you use agents with live Mobazha listing tools. Require the agent to draft changes first, show changed fields, get explicit approval before create or update calls, and cap or dry-run any bulk listing edits.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly says it can publish directly via listings_create and listings_update, but provides no safety guidance about confirming changes before modifying live marketplace content. This creates a real risk of unintended listing creation or overwriting if an agent follows the workflow automatically, especially in a commerce context where listing accuracy affects sales, reputation, and compliance.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example workflow instructs the agent to fetch a listing, rewrite it, and call listings_update without any mention of preview, diff review, or user approval. That omission is dangerous because it normalizes direct overwriting of existing listing content, which could damage product accuracy, SEO performance, legal disclosures, or brand voice at scale.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The bulk-generation workflow encourages automated improvements across multiple products based on weak heuristics like 'short or generic descriptions' but includes no limits, batching, confirmation, or review controls. In a marketplace setting, bulk automated updates can rapidly propagate low-quality, inaccurate, or noncompliant copy across many listings, amplifying business and trust impact beyond a single-item edit.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.