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.ai API 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-gateway for handling other third-party integrations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 01:51 PM
Security Audit — agent-trust-hub — zoho-bigin