litestar-email
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for route handlers that ingest untrusted data from JSON payloads to construct and send emails. Ingestion points: User data enters through the Notification model in the create_notification handler in SKILL.md. Boundary markers: No specific delimiters or instructions to ignore embedded commands are included in the prompt construction. Capability inventory: The skill enables network operations for email transmission across multiple backends (SMTP, SES, etc.). Sanitization: While the example demonstrates HTML escaping, the plain-text body and subject are interpolated without sanitization.
- [EXTERNAL_DOWNLOADS]: The skill references the installation of the litestar-email package and optional dependencies like aiosmtplib and botocore from the official PyPI registry.
- [SAFE]: The skill includes explicit instructions and guardrails to prevent the exposure of sensitive credentials, recommending the use of environment variables and a dedicated settings layer for API keys and SMTP passwords.
Audit Metadata