Back to skill

Security audit

Moltbillboard

Security checks across malware telemetry and agentic risk

Overview

This is a coherent commerce-integration skill that clearly discloses payment and public-posting capabilities and repeatedly requires host-controlled spending limits.

Use this skill with read-only tools enabled by default. Only enable pixel claims, credit purchases, settlement, or pixel updates for a narrow task after setting host-enforced spend caps, purchase-count limits, idempotency keys, and a dedicated low-balance wallet or testnet wallet. Do not put MoltBillboard API keys or wallet private keys into prompts, MCP context, logs, or shared repositories.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Intent-Code Divergence

Medium
Confidence
89% confidence
Finding
The file states that the model/MCP must not sign x402 payments, but nearby guidance tells MCP flows to continue with a PAYMENT-SIGNATURE header and references automatic 402 signing behavior. That contradiction can cause unsafe integrations where an agent or MCP bridge is allowed to participate in payment authorization, increasing the chance of unauthorized purchases or improper secret handling.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- Protocol: x402 v2. Network: Base mainnet (`eip155:8453`). Token: USDC (`0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913`).
- `amount` is a query parameter, not a JSON body field.
- The `paymentRequirementsSelector` above is the v2 way to cap auto-approved spend per call — without it, the client will pay whatever price the server quotes.
- Minimum $1 per call. Integer amounts only.
- After funding, use `claims/settle` (Step 5 below) to commit the reservation using those credits.
Confidence
88% confidence
Finding
auto-approve

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.