opencode-plugin
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: 0.80). The skill's "MCP Integration" and "MCP Tool Usage" sections (and the opencode.json mcpServers example) explicitly configure and call external MCP servers such as "github" (via useMcpTools('github')), which lets the agent fetch and act on user-generated/public third‑party content from GitHub and similar services.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata