image-skill

Warn

Audited by Snyk on Jun 23, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The docs repeatedly instruct running npx to fetch and execute remote CLI code at runtime (e.g., "npx -y image-skill@latest" which pulls code from the npm registry and the install form "npx skills add https://image-skill.com"), so the runtime will fetch and execute remote package content from the npm registry / https://image-skill.com.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). The skill includes explicit, built-in payment rails and commands for quoting and buying credits (e.g., credits quote, credits buy, credits status) and documents specific payment providers and flows (Stripe x402.exact.usdc, stripe_checkout). It returns payable instructions and wallet-settlement fields (Base/USDC amount, deposit address) and supports an "agent_settleable" browserless x402 path for agent-controlled wallet settlement. These are concrete payment gateway and wallet-settlement capabilities (quote → buy → settlement), not merely generic HTTP or browser automation, so the skill grants direct financial execution authority.

Issues (2)

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 23, 2026, 01:51 AM
Issues
2
Security Audit — snyk — image-skill