caffeine-app

Warn

Audited by Snyk on Nov 19, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). The required workflow pulls community-published packages from public registries (mops add and npm installs, plus component skills restored via npx skills experimental_install from a lock file), which an agent can select but an outsider cannot force into the workflow, so this is low; the other fetched sources (writing-motoko, caffeinelabs skills, bindgen output, the CLI's own status and build output) are first-party or own-tenant.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 19, 2026, 06:57 AM
Issues
1