agentmail

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill inherently processes untrusted data from external sources (inbound email content).
  • Ingestion points: The SKILL.md file defines methods to fetch message details, including bodyText and bodyHtml from the AgentMail API.
  • Boundary markers: The skill does not explicitly define delimiters or instructions for the agent to ignore potentially malicious instructions embedded within retrieved email content.
  • Capability inventory: The agent possesses the capability to send outgoing emails, manage webhooks, and interact with the AgentMail REST API based on the information it reads.
  • Sanitization: There is no evidence of sanitization or filtering of the incoming email body before it is presented to the agent's context. This is a common characteristic of communication-based tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 12:29 PM
Security Audit — agent-trust-hub — agentmail