netsuite
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official Membrane CLI tool (
@membranehq/cli) via npm. This is a standard requirement for the platform and originates from the skill's vendor infrastructure. - [CREDENTIALS_UNSAFE]: The skill demonstrates safe security practices by utilizing managed connections (
membrane connection ensure) instead of hardcoding or requesting raw API keys, which ensures secrets remain within the platform's secure environment. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external NetSuite records, which represents a potential attack surface for indirect prompt injection if malicious data is present in those records.
- Ingestion points: Data retrieved from NetSuite via
membrane action runormembrane request(SKILL.md). - Boundary markers: None explicitly defined in the provided instructions.
- Capability inventory: The skill can perform NetSuite actions (listing, creating, updating records) and make arbitrary proxied HTTP requests via the
membrane requestcommand. - Sanitization: No specific sanitization or validation logic is defined within the skill's instructional text.
Audit Metadata