alegra
Warn
Audited by Snyk on Oct 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill instructs the agent to interact with Alegra data and invoices via Membrane, which can ingest external records and invoices containing outsider-authored free text.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (medium risk: 0.30). The skill integrates with Alegra (cloud accounting/invoicing software) via the Membrane CLI, supporting actions such as "Create Payment", "Create Bill", and "Create Invoice" (SKILL.md:126-128). Creating payments and bills represents indirect or direct financial operations (invoicing, bill creation, payment records) tied to accounting software. However, the connection is authenticated and managed via the Membrane platform (
membrane login,membrane connection ensure), which handles user authentication and OAuth/API key credential storage server-side (SKILL.md:34, 47, 67, 176). The underlying service access is authenticated.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata