imap-smtp-email

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external email servers, creating a vulnerability surface where malicious instructions embedded in emails could influence agent behavior.
  • Ingestion points: The scripts/imap.js file fetches email bodies and snippets via fetch, search, and check commands.
  • Boundary markers: The skill does not implement or recommend specific delimiters or prompt-level warnings to distinguish untrusted email content from system instructions.
  • Capability inventory: The skill possesses the capability to send emails (scripts/smtp.js) and write files to the disk (scripts/imap.js download command), which could be abused if an injected instruction is followed.
  • Sanitization: Filename sanitization is performed in scripts/imap.js to prevent directory traversal, but email body content is passed to the agent without specific sanitization against prompt injection patterns.
  • [COMMAND_EXECUTION]: The skill relies on executing local Node.js scripts to perform its primary functions, which is the intended behavior for this type of tool.
  • Evidence: SKILL.md defines commands for checking, fetching, searching, and sending emails by invoking node scripts/imap.js and node scripts/smtp.js.
  • Mitigation: The scripts implement validateReadPath and validateWritePath functions that enforce a whitelist of directories defined in the ALLOWED_READ_DIRS and ALLOWED_WRITE_DIRS environment variables, preventing arbitrary file access.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:11 AM