zoho-bigin
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
@membranehq/cliutility from the NPM registry to facilitate authentication and API interactions with the Membrane platform. - [INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from external Zoho Bigin modules, creating an attack surface for indirect prompt injection.
- Ingestion points: Data from Zoho Bigin records, users, and layouts retrieved via the
membrane action runandmembrane requestcommands inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' markers to isolate external CRM data from agent commands.
- Capability inventory: The agent can execute CRM actions and perform arbitrary API requests through the
membraneCLI tool. - Sanitization: No explicit sanitization or filtering logic is described for the data retrieved from the external CRM before it is consumed by the AI agent.
Audit Metadata