gangtise-kb
Warn
Audited by Snyk on Mar 11, 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's core workflows (scripts/query_kb.py and scripts/download_resource.py as described in SKILL.md) query the Gangtise knowledge API and explicitly surface/return third-party web content and URLs (notably resource types 80/90 "网络资源/公众号" which "返回 URL") and then display or download and clean that content, meaning untrusted, public web content is fetched and interpreted as part of normal operation.
Audit Metadata