haah

Warn

Audited by Snyk on Apr 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill routinely calls the external haah.ing API (e.g., GET /heartbeat, GET /dispatch/pending, GET /connect/:token) and ingests user-generated answers from dispatch.requests and inbox.requests which the agent reads, interprets, and uses to draft/send replies or decide follow-up actions, exposing it to untrusted third-party content that could carry indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 10, 2026, 01:50 AM
Issues
1