ben-agent-email
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon inbound emails from external senders, which is a classic vector for indirect prompt injection where an attacker could send an email containing hidden instructions to influence the agent.
- Ingestion points: Inbound emails received via the Resend webhook handler defined in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to separate untrusted email data from the agent's core logic.
- Capability inventory: The agent has the authority to send replies, process attachments, and update session states based on the content of these external emails.
- Sanitization: There is no mention of sanitizing or filtering the email body for potential injection patterns before processing.
Audit Metadata