skills/caffeinelabs/skills/email/Gen Agent Trust Hub

email

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface where untrusted user input is interpolated into email content.
  • Ingestion points: The parameters username and orderReference in main.mo are used to construct the email body.
  • Boundary markers: None. There are no delimiters or instructions provided to the agent to ignore potentially malicious content within these variables.
  • Capability inventory: The skill utilizes the EmailClient.sendServiceEmail function to send emails to external recipients.
  • Sanitization: No sanitization or escaping of the input variables is performed before they are concatenated into the final body string, which could allow for content injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:39 PM
Security Audit — agent-trust-hub — email