media-generation
Warn
Audited by Snyk on Apr 19, 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 skill requires running "npx agentcash@latest fetch" at runtime (e.g., "npx agentcash@latest fetch https://stablestudio.dev/..."), which pulls and executes remote npm package code (agentcash) on the host, so the agent depends on and will execute externally-fetched code.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill is explicitly tied to paid usage and a payment-enabled CLI: it instructs "Generate images and videos via x402 payments" and requires using the agentcash CLI ("ALWAYS use
npx agentcash@latest fetch") and wallet setup. The docs show paid endpoints with per-job costs and state thatfetch"handles paid submission requests" (and mentions wallet setup and SIWX). This is not merely a generic HTTP or browser tool — it explicitly references a payment mechanism and a wallet/CLI used to submit paid transactions, which enables the agent to initiate monetary transactions to consume the service. Therefore it provides specific financial execution capability.
Issues (2)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata