email-imap-full-fetch
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external IMAP server which could contain malicious instructions.
- Ingestion points: Email headers, plain text bodies, and HTML bodies are fetched from the remote IMAP server via
scripts/imap_full_fetch.py. - Boundary markers: The skill returns data in a structured JSON format, but does not provide explicit instructions to the agent to ignore or delimit embedded instructions within the email content.
- Capability inventory: The skill allows writing files to the local file system (
.emlfiles and attachments) and performing network connections to the configured IMAP host. - Sanitization: The script implements
sanitize_filenameusing a strict whitelist regex ([^A-Za-z0-9._-]+) and filters attachments by extension and size, though it does not sanitize the natural language content of the email body itself.
Audit Metadata