zoho-email
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of untrusted data from external email messages.
- Ingestion points: Data from external senders enters the agent's context through subjects, bodies, and sender details retrieved via the
searchandgetcommands inscripts/zoho-email.py. - Boundary markers: The instructions do not define clear delimiters or specify that the agent should ignore instructions embedded within email data.
- Capability inventory: The agent has the capability to send emails (
send,send-html), delete or move messages (delete,move), and manage attachments (download-attachment), which could be leveraged by an attacker if the agent obeys instructions found in a message. - Sanitization: There is no evidence that the retrieved email content is sanitized or validated before being presented to the agent.
- [EXTERNAL_DOWNLOADS]: Fetches the
requestslibrary from the official Python Package Index (PyPI) to facilitate API communication with Zoho's servers.
Audit Metadata