opencode-agent-authoring
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains purely instructional content for authoring agent and skill documentation. It defines clear boundaries and syntax requirements for agent behavior files.
- [INDIRECT_PROMPT_INJECTION]: The skill involves creating and updating instructions (e.g., in
.opencode/agent/*.md). While this is an ingestion surface, it is consistent with the skill's primary purpose of documentation management and does not present an exploitable vulnerability surface in its current static form.
Audit Metadata