misoapps

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill handles untrusted external data through email delivery and logging functions, establishing an indirect prompt injection surface.
  • Ingestion points: Content processed via sendEmail, sendSystemEmail, and log data returned from getEmailLogs in SKILL.md.
  • Boundary markers: The SDK usage examples do not demonstrate the use of delimiters or instructions to the agent to ignore potentially malicious content within email bodies or subjects.
  • Capability inventory: The skill allows for network operations (sending emails) and application management (installing/updating shop apps).
  • Sanitization: No specific input sanitization or validation logic is presented in the integration examples.
  • [EXTERNAL_DOWNLOADS]: The skill documentation requires the installation of the @misoapps/mail-sdk and @misoapps/shop-sdk packages from the NPM registry.
  • [DATA_EXFILTRATION]: The SDK methods are designed to transmit sensitive authentication data, such as Shopify access tokens and SMTP passwords, to the service's API endpoints at mail-api.misoapps.com and shop-api.misoapps.com.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 09:14 PM