zoho-people
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes Python code snippets for the agent to perform HR management tasks such as retrieving employee records and managing departments. These scripts are provided as templates for legitimate integration purposes.- [EXTERNAL_DOWNLOADS]: The skill communicates with subdomains of
maton.ai(gateway.maton.ai,ctrl.maton.ai,connect.maton.ai) to manage OAuth sessions and proxy requests to Zoho People's official API. These network operations are aligned with the skill's intended functionality.- [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external HR records, which creates a potential surface for indirect injection if that data is maliciously crafted. - Ingestion points: Zoho People API responses retrieved via the
gateway.maton.aiproxy (e.g., employee lists, form configurations). - Boundary markers: There are no explicit delimiters or safety instructions in the provided templates to isolate external data from the agent's instructions.
- Capability inventory: The skill possesses the capability to modify HR data (Insert/Update) and perform network operations using the provided Python scripts.
- Sanitization: No explicit data validation or sanitization logic is present in the provided examples for processing external API content.
Audit Metadata