agents-chat-cli@3.38.3
多智能体群聊工具 - 支持 OpenCode/Claude Code/Codex/pi 内核,微信风格聊天界面
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe automatic postinstall global installation is a concrete install-hook risk. Source inspection found no self-dependency, concealed payload, credential harvesting, or exfiltration, so the evidence does not support a malicious classification.
Decision evidence
public snapshot- The package runs a postinstall hook automatically during npm installation.
- That hook installs opencode-ai globally when no supported AI CLI is detected.
- The global installation is enabled by default; it is only skipped when an environment variable is set.
- The package can later write a custom provider and API key into the user's OpenCode configuration.
- The installer names the exact command and dependency rather than hiding or obfuscating it.
- No self-dependency, credential harvesting, secret exfiltration, or unrelated network endpoint was found.
- Configuration writes occur in runtime functions for user-supplied custom LLM settings, not in the install hook.
Source & flagged code
19 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgA bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to agents-chat-cli@3.38.3.
See all versions of agents-chat-cli for other recorded verdicts.
- Review the evidence and your use of agents-chat-cli@3.38.3 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.