findymail
Warn
Audited by Snyk on Apr 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to run Findymail actions and to proxy arbitrary requests via "membrane request" (e.g., "find-email-by-linkedin" and "find-phone-number" which ingest data from public LinkedIn profiles and other user-generated sources), so the agent will read and act on untrusted third-party content returned by those APIs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata