council

Warn

Audited by Snyk on May 6, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly requires multi-agent web research in Phase 1 (default "纯网络搜索") and tools like "council download-subtitles <YouTube_URL>" and parallel agents that fetch/search public web, podcasts, YouTube, blogs and write those research files (personas/.../research/*) — meaning the agent autonomously ingests untrusted, user-generated third‑party content which is then used to drive persona construction and subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 6, 2026, 06:08 AM
Issues
1