genjo-ai-news
Warn
Audited by Snyk on Apr 8, 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.md workflows explicitly require calling get_latest_news and get_news_detail to retrieve and cite news from external/public sources and then analyze/synthesize those items (including fact-checks and investment actions), so the agent ingests and acts on untrusted third-party news content that could carry embedded instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata