NYC

sobriety-tools-guardian

Warn

Audited by Snyk on Feb 15, 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). Yes — multiple scripts (e.g., scripts/cache-health.ts, scripts/perf-audit.ts, and scripts/crisis-path-test.ts) fetch and parse JSON and headers from the third‑party meeting proxy at https://jb4l-meeting-proxy.erich-owens.workers.dev (and fetch remote sw.js), meaning the agent ingests external, potentially untrusted/public content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:27 PM