finastra
Warn
Audited by Snyk on Apr 30, 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 and instructs running remote CLI code (e.g., "npm install -g @membranehq/cli@latest" or "npx @membranehq/cli@latest"), which fetches and executes code from the npm registry at runtime and is a required dependency for the skill.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill is a dedicated Finastra (banking) integration exposing banking-specific entities and operations — e.g., Payment, Standing Order, Direct Debit, Beneficiary, Account/Transaction — and describes using Membrane to create/run actions on a connected Finastra account. These are explicit banking/payment operations (not generic tools like a browser or generic HTTP caller), so the skill is specifically designed to operate on financial instruments and can be used to send/manage payments and standing orders. Therefore it grants direct 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