substack

Warn

Audited by Snyk on May 9, 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's chat-reply flow (SKILL.md, "ユースケース3: チャットスレッドの新着返信を処理する") calls chat_check.py to fetch new Substack chat replies (user-generated/public comments) as JSON, which the agent is expected to read, interpret, and use to draft and post replies—allowing untrusted third-party content to influence tool actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 9, 2026, 06:45 AM
Issues
1
Security Audit — snyk — substack