opencode-v2-config
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read, parse, and transform existing configuration data (e.g., V1 to V2 migration). This processing of external data creates a surface where malicious instructions embedded in a configuration file could influence the agent's behavior.
- Ingestion points: The agent is directed to locate and read
opencode.jsonfiles from various project directories and global configuration paths like~/.config/opencode/. - Boundary markers: The instructions do not define explicit delimiters or security warnings to ensure the agent treats configuration values as passive data rather than executable instructions.
- Capability inventory: The agent is authorized to generate file content, write configuration files, and interact with specific API endpoints (
POST /api/session/{id}/model). - Sanitization: There are no specific instructions to validate or sanitize values extracted from the input files before processing them.
Audit Metadata