email-imap-fetch
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external emails.
- Ingestion points: Remote email subjects and bodies are fetched using the
imapliblibrary inscripts/imap_idle_fetch.py. - Boundary markers: The script does not wrap email content in protective delimiters or provide instructions to downstream agents to ignore embedded commands.
- Capability inventory: The skill possesses network capabilities to forward data to webhooks and outputs data in JSONL format for agent consumption.
- Sanitization: The script uses a regular expression
HTML_TAG_REto strip HTML tags andSPACE_REto normalize whitespace, but it does not sanitize plain-text natural language instructions.
Audit Metadata