imapflow
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill documents the use of a legitimate, well-known Node.js library (imapflow) and follows security best practices by using placeholders for authentication credentials and warning against disabling TLS certificate validation in production.
- [PROMPT_INJECTION]: The skill allows the agent to ingest email content from external sources, which is a known surface for indirect prompt injection attacks. 1. Ingestion points: The skill uses client.fetch(), client.fetchOne(), and client.download() to retrieve email bodies and attachments. 2. Boundary markers: No specific delimiters or instructions to ignore embedded commands are included in the skill documentation. 3. Capability inventory: The skill enables reading, searching, moving, and deleting emails; it does not explicitly request other system-level permissions. 4. Sanitization: There is no mention of sanitizing or filtering fetched content before the agent processes it.
Audit Metadata