registry / @masiy_0104/open-coder / 0.9.0

@masiy_0104/open-coder@0.9.0

🤖 开源安全的命令行 AI 编程助手，支持本地部署和国产模型

AI Security Review

scanned 13h ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

One or more suspicious static signals were detected.

Trigger

User runs the CLI, submits a prompt, and approves a spawned-task operation.

Impact

Prompt injection or unsafe model output can modify files or execute commands as the user; selected project context can be disclosed to the configured model API.

Mechanism

LLM-directed shell/filesystem tools with incomplete confirmation coverage

Rationale

No install-time execution or concrete malicious chain was found. The package is a benign-intent coding assistant, but its unguarded sub-agent execution is a material dangerous capability.

Evidence

package.jsonsrc/tools/index.tssrc/task-scheduler.tssrc/agent.tssrc/context.tssrc/config.tssrc/updater.tsREADME.mdtsconfig.jsonCargo.tomlpyproject.tomlgo.modpom.xmlbuild.gradledocker-compose.ymlDockerfile

Network endpoints4

/compatible-mode/v1

@masiy_0104/open-coder@0.9.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code