opencode

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly exposes the agent to untrusted third‑party content via built‑in tools like "webfetch" and "websearch" (listed in SKILL.md / tools) and via the GitHub integration (reference/github-integration.md) which ingests public Issue/PR comments and runs actions based on their content, allowing user-generated content to influence agent decisions and tool use.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill contains a direct install command that fetches and executes remote code via "curl -fsSL https://opencode.ai/install | bash", which runs code from that URL on the user's machine and thus is a high-risk runtime/execution dependency.