@omega3_0/nanoagent@2.1.15
Ultra-lightweight, scalable CLI/TUI coding agent optimized for tiny local models & remote runtimes
AI Security Review
scanned 2mo ago · by lpm-firewall-aiSource inspection found a normal coding-agent CLI rather than concrete malicious behavior. The flagged shell, network, and environment primitives are user-driven product features with relevant safeguards.
Decision evidence
public snapshot- The manifest has CLI entry points but no install lifecycle hook.
- Bun installation is offered only after an interactive affirmative response.
- Agent tool execution checks permission and sanitizes output.
- Project-local MCP servers are blocked from automatic connection.
- No credential harvesting or unsolicited exfiltration was found.
- No persistence, destructive install action, or hidden payload execution was found.
- Network features are configured LLM and MCP client functionality.
Source & flagged code
7 flagged · loading sourcePackage source references dynamic require/import behavior.
dist/graph/MemoryGraph.jsView on unpkg · L345Package source references weak cryptographic algorithms.
dist/mcp/index.jsView on unpkg · L16Findings
Affected versions and remediation
This report applies to @omega3_0/nanoagent@2.1.15.
See all versions of @omega3_0/nanoagent for other recorded verdicts.
- Review the evidence and your use of @omega3_0/nanoagent@2.1.15 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.