zoho-bigin
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on shell commands executed via
npx @useclawlink/clito interact with Zoho Bigin. These commands are used for logging in, connecting the account, and executing CRM actions. - [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external Zoho Bigin records which constitutes a surface for indirect prompt injection.
- Ingestion points: Data is ingested via
npx @useclawlink/cli run zoho-biginwhen reading contacts or pipeline data. - Boundary markers: The instructions include a clear boundary: 'Reads first; confirm with the user before any write.'
- Capability inventory: The skill has the capability to execute shell commands and write to the CRM through the CLI tool.
- Sanitization: No automated sanitization is specified in the prompt instructions, relying instead on manual user review for write operations.
Audit Metadata