zoho-bigin
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from Zoho Bigin modules, which represents a potential surface for indirect prompt injection if record content contains malicious instructions.\n
- Ingestion points: CRM record data retrieved via the
gateway.maton.aiAPI endpoints.\n - Boundary markers: Absent; there are no instructions to the agent to treat retrieved data as untrusted or to ignore embedded commands.\n
- Capability inventory: The skill allows for comprehensive CRM operations including listing, creating, updating, and deleting records in various modules (Contacts, Accounts, Pipelines, etc.).\n
- Sanitization: Absent; the provided code snippets show direct processing of API responses without validation or escaping.\n- [COMMAND_EXECUTION]: Provides Python and shell-based templates for the agent to interact with the API gateway, including the use of heredocs to execute multi-line scripts.\n- [EXTERNAL_DOWNLOADS]: References an external skill hosted at
clawhub.ai/byungkyu/api-gatewayfor handling other third-party integrations.
Audit Metadata