Mails for Agent
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill does not contain hardcoded credentials, malicious code, or unauthorized external references. Its behavior is consistent with its stated purpose of providing email access to an agent.
- [PROMPT_INJECTION]: The skill processes untrusted data from incoming emails, creating a surface for indirect prompt injection.
- Ingestion points: Email bodies and subjects retrieved through the
/api/inboxand/api/emailendpoints defined in SKILL.md. - Boundary markers: None; the skill does not instruct the agent to use delimiters or ignore instructions within email content.
- Capability inventory: The agent can send emails, delete messages, and update mailbox configurations including webhooks via the provided POST, PUT, and PATCH endpoints.
- Sanitization: There are no instructions for sanitizing or validating the content received from external senders before processing.
Audit Metadata