skills/vm0-ai/vm0-skills/zeptomail/Gen Agent Trust Hub

zeptomail

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses bash -c and curl to interact with the ZeptoMail API. This behavior is consistent with the skill's primary purpose of sending emails via a command-line interface.
  • Ingestion points: User-provided email addresses, subject lines, HTML/text body content, and template merge fields are ingested and written to /tmp/zeptomail_request.json in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded instructions are present in the provided examples.
  • Capability inventory: The skill utilizes bash, curl, and base64 across all Send Mail examples.
  • Sanitization: No explicit sanitization or filtering of user-provided content is implemented within the shell commands.
  • [EXTERNAL_DOWNLOADS]: The skill connects to api.zeptomail.com, which is the official well-known service domain for Zoho ZeptoMail.
  • [DATA_EXFILTRATION]: Authentication is handled via the ZEPTOMAIL_API_KEY secret defined in the skill's metadata. No unauthorized network operations or access to sensitive local files were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 07:15 AM