imap-smtp-email
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves data from external email servers that may contain malicious instructions designed to manipulate agent behavior.\n
- Ingestion points: Commands in
scripts/imap.js(specificallycheck,fetch, andsearch) ingest email subjects, bodies, and attachment metadata from remote IMAP servers.\n - Boundary markers: The skill does not utilize specific delimiters or instructions to treat the external email content as untrusted data.\n
- Capability inventory: The skill is capable of reading local files (via
scripts/smtp.jsfor attachments), writing local files (viascripts/imap.jsfor attachment downloads), and performing network operations (IMAP and SMTP).\n - Sanitization: There is no evidence of sanitization or safety-filtering performed on email data before it is presented to the agent.
Audit Metadata