initiate-inboxmate-knowledge

Warn

Audited by Snyk on Apr 24, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly states that knowledge buckets are created by scraping URLs (items with source_type 'url'/'knowledge_link') and that demo pages (publicly served via demo.inboxmate.psquared.dev) and scraped knowledge are read/checked during QA and used to generate email drafts, so untrusted third‑party web content is ingested and can materially influence decisions like marking OK_TO_SEND and creating/sending outreach.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 24, 2026, 07:07 AM
Issues
1
Security Audit — snyk — initiate-inboxmate-knowledge