ClawHub
Back to skill

Security audit

eBay

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown eBay selling guide with no executable code, persistence, credential access, or hidden installation behavior.

Review the international shipping advice before relying on it; prefer eBay-supported eligibility, tracked shipping, signature confirmation, and transaction-specific risk controls over blanket country exclusions. Otherwise, the skill behaves like a static reference guide.

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

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 94)May include surrounding context.

md
- **Underestimating shipping** → eat costs on heavy items; weigh and measure BEFORE listing
- **Ignoring item specifics** → listings without specs get buried in search
- **Accepting PayPal without verification** → chargebacks on high-value items; require signature for >$750
- **Pricing from asking, not sold** → unsold listings don't reflect market; filter by SOLD
- **Shipping before payment clears** → "Item Not Received" claims; wait for funds

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advises excluding specific countries using broad fraud-risk labels without user opt-in, evidence, or a documented policy basis. This can encourage discriminatory seller behavior, create compliance and fairness issues, and cause users to make decisions based on stereotypes rather than transaction-specific risk controls.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.