zoho-crm
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides multiple examples that execute Python code directly from the shell using heredocs (
python <<'EOF'). These scripts utilize standard libraries to interact with the environment and perform network requests. - [INDIRECT_PROMPT_INJECTION]: The skill processes record data (such as Leads and Contacts) retrieved from Zoho CRM. This data is externally controlled and could potentially contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Data is ingested through API responses from
https://gateway.maton.ai/zoho-crm/crm/v8/endpoints inSKILL.md. - Boundary markers: The provided code examples do not use specific delimiters or instructions to prevent the agent from obeying text embedded within CRM record fields.
- Capability inventory: The skill utilizes scripts capable of performing network requests, modifying CRM records, and executing Python code.
- Sanitization: There is no evidence of sanitization, validation, or filtering of the content retrieved from the CRM modules before it is processed by the agent.
Audit Metadata