longbridge-news
Warn
Audited by Snyk on May 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: 0.90). The skill explicitly ingests Longbridge community topics via MCP (mcp__longbridge__topic / topic_replies) and — per the required "WebSearch fallback" section in SKILL.md — performs web searches of public sites when MCP is empty or stale, meaning the agent reads untrusted user-generated/open-web content and uses it to drive classification and downstream outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata