imap-smtp-email
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted email content from remote IMAP servers, which constitutes a surface for Indirect Prompt Injection.
- Ingestion points: Email bodies and attachments are retrieved and parsed in
scripts/imap.js. - Boundary markers: The implementation does not include specific boundary markers or instructions to the agent to disregard potential instructions embedded in email content.
- Capability inventory: The skill possesses capabilities for filesystem writes (restricted by a whitelist) and network communication (sending emails via SMTP).
- Sanitization: Basic sanitization is performed on filenames, and the skill leverages the standard
mailparserlibrary for content handling. - [COMMAND_EXECUTION]: The
setup.shscript facilitates the installation of the skill's environment by executingnpm install, a standard operational step for Node.js applications. - [EXTERNAL_DOWNLOADS]: During setup, the skill downloads required dependencies from the npm registry, which is a recognized and well-known service.
Audit Metadata