agentmail

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from external emails, which serves as an ingestion point for indirect prompt injection.
  • Ingestion points: The scripts/check_inbox.py script and the agentmail SDK fetch message snippets, subjects, and headers from the AgentMail service into the agent's context.
  • Boundary markers: While the SKILL.md includes a manual warning for the agent to treat incoming content as untrusted, no programmatic boundary markers or delimiters are implemented in the provided scripts to isolate external content.
  • Capability inventory: The skill provides capabilities to send emails through the scripts/send_email.py utility and the SDK, which could be exploited if the agent follows malicious instructions contained in received messages.
  • Sanitization: No programmatic filtering, sanitization, or validation of incoming email content is performed before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 10:45 AM
Security Audit — agent-trust-hub — agentmail