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/inbox and /api/email endpoints 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
Risk Level
SAFE
Analyzed
Jun 15, 2026, 02:06 PM
Security Audit — agent-trust-hub — Mails for Agent