easy-opencode

• Analyzed: May 11, 2026, 4:35 AM
• Findings: 1
• Version: 1.1.1
• Hash: 1481417457bb73be9c0830674098f7a4fb7c11092706e18310438aa3d54fc88f
• Source: palm
• External report: View on VirusTotal

Findings (1)

The skill instructs the agent to execute an external binary `opencode` via shell commands (`cd [repo dir] && opencode run "[instructions/questions]" ...`) as seen in `SKILL.md`. The `[instructions/questions]` argument is likely derived from user input or agent-generated content. Without explicit sanitization or escaping of this argument before it's embedded into the shell command, this creates a significant shell injection vulnerability, potentially leading to arbitrary code execution (RCE) on the host system. The `opencode` binary itself is an unknown dependency, and its capabilities are not specified, adding to the overall risk.