@aiyiran/myclaw@1.1.209
为 OpenClaw 教学环境设计的一站式命令行工具。
AI Security Review
scanned 16d ago · by lpm-firewall-aiSource inspection found user-invoked agent configuration writes but no npm install lifecycle hook or concrete malicious behavior. The configuration capability warrants a warning under the agent integration policy.
Decision evidence
public snapshot- The manifest has no preinstall, install or postinstall hook; its only script is a placeholder test command.
- Creating an agent writes a new entry to the OpenClaw agent configuration and creates agent workspace files.
- The agent creation flow prompts for an agent name before creating it, and the wizard registers an agent through a separate step.
- The reviewed agent configuration changes are user-invoked setup behavior; the inspected excerpts show no hidden install-time mutation or data transmission.
Source & flagged code
21 flagged · loading sourcePackage source references dynamic require/import behavior.
delete_agents.jsView on unpkg · L19Findings
Affected versions and remediation
This report applies to @aiyiran/myclaw@1.1.209.
See all versions of @aiyiran/myclaw for other recorded verdicts.
- Review the evidence and your use of @aiyiran/myclaw@1.1.209 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.