hokipoki

Warn

Audited by Snyk on Mar 24, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill sends tasks to and consumes JSON responses from remote AI providers via "hokipoki request" (see SKILL.md "Requesting Help from Another AI") and may auto-apply returned patches ("Patch Auto-Apply"), so untrusted third-party provider/model outputs can directly influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 24, 2026, 12:27 AM
Issues
1