opencode
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is comprised entirely of markdown-based documentation in the SKILL.md file. It does not include any scripts, configuration files, or binaries that could be executed or used to perform actions.
- [SAFE]: The content is purely informational, describing how agents, tools, and skills are structured within the OpenCode framework. It includes examples of configuration files (opencode.jsonc) and API endpoints (http://localhost:3111) for educational purposes to assist the agent in debugging or extending the framework.
- [SAFE]: No instances of prompt injection, obfuscation, or data exfiltration attempts were identified. All mentioned external resources, such as the Vercel AI SDK and Kortix endpoints, are documented as standard components of the author's own ecosystem.
Audit Metadata