pua-ja

Warn

Audited by Snyk on Mar 13, 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). Yes — the SKILL.md explicitly requires the agent to "主体的に検索しろ" and "原典を読め" (including searching "official documentation + Issues" and full error messages), which mandates fetching and reading open/public third‑party pages and user‑generated content (e.g., issues, forums) as part of its required workflow, allowing that content to materially influence next actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 13, 2026, 02:41 PM
Issues
1