agent-mail
Warn
Audited by Snyk on Nov 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The agent reads agent mail inboxes and message threads sent by other external agents or human overseers via tools like
fetch_inboxand resources likeresource://inbox/{agent}.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill documentation references installation scripts and package repositories via HTTPS URLs (raw.githubusercontent.com and npmjs/npx) to fetch and execute setup commands, constituting a weak/unknown external operational dependency.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata