registry / @omega3_0/nanoagent / 2.1.16
@omega3_0/nanoagent@2.1.16
Ultra-lightweight, scalable CLI/TUI coding agent optimized for tiny local models & remote runtimes
AI Security Review
scanned 2mo ago · by lpm-firewall-aiStatic source inspection found a normal coding-agent CLI with user-invoked network and command capabilities, plus explicit protections for secrets and untrusted project MCP configuration. No malicious lifecycle hook, stealth execution, payload staging, or concrete exfiltration chain was found.
Static reason
No blocking static signals were detected.; source matched previously finalized malicious package; routed for review
Trigger
A user runs the CLI or TUI and chooses configured agent actions.
Impact
No unconsented persistence, credential exfiltration, destructive action, or foreign agent-control-surface mutation was confirmed.
Mechanism
User-directed coding-agent execution with configured model and MCP connections.
AI rationale
Static source inspection found a normal coding-agent CLI with user-invoked network and command capabilities, plus explicit protections for secrets and untrusted project MCP configuration. No malicious lifecycle hook, stealth execution, payload staging, or concrete exfiltration chain was found.
Evidence
package.jsondist/main.jsdist/agent-lifecycle.jsdist/mcp/index.jsdist/config/api-keys.jsdist/security/index.jsdist/tools/exec-tools.js
Decision evidence
public snapshotAI called this Clean at 96.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest has no preinstall, install, or postinstall lifecycle hook; execution is through declared CLI entry points.
- The Bun installer path is reached only after an interactive TTY prompt and an explicit yes response.
- Project-local MCP servers are blocked from automatic connection unless a trusted source or explicit environment override permits them.
- MCP file interpolation rejects paths outside the workspace and applies the blocked-file guard.
- API keys are read from the process environment or trusted home-directory files, not a workspace .env file.
Evidence against
- The user-invoked coding-agent CLI can run shell commands and contact configured model or MCP endpoints.
- The interactive TUI can install Bun after explicit confirmation.
- The package uses dynamic imports for optional runtime and UI paths.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
Source & flagged code
6 flagged · loading sourcedist/graph/MemoryGraph.jsView file
345if (ts.isImportDeclaration(node)) {
L346: this.processTSImport(node, fileNode, sf);
L347: }
Medium
Dynamic Require
Package source references dynamic require/import behavior.
dist/graph/MemoryGraph.jsView on unpkg · L345dist/mcp/index.jsView file
16.replace(/\{env:([^}]+)\}/g, (_, varName) => {
L17: return process.env[varName] ?? '';
L18: })
...
L31: }
L32: // Refuse to interpolate blocked files (workspace .env, private keys,
L33: // etc.) into MCP server env/headers — that would exfiltrate secrets.
...
L81: this.configs = configs ?? {};
L82: this.workspace = workspace || process.cwd();
L83: }
...
L200: cwd: config.cwd ?? this.workspace,
L201: // Never inherit stderr into the TUI — MCP servers (Serena especially)
L202: // emit INFO logs that corrupt the OpenTUI screen.
Low
Weak Crypto
Package source references weak cryptographic algorithms.
dist/mcp/index.jsView on unpkg · L16skills/microsoft-foundry/models/deploy-model/capacity/scripts/discover_and_rank.sh
Findings
3 High5 Medium5 Low
HighKnown Malware Source Similaritydist/main.js
HighKnown Malware Source Similaritydist/subagents/pool.js
HighKnown Malware Source Similaritydist/bun-detect.js
MediumDynamic Requiredist/graph/MemoryGraph.js
MediumNetwork
MediumEnvironment Vars
MediumShips Build Helperskills/microsoft-foundry/models/deploy-model/capacity/scripts/discover_and_rank.sh
MediumStructural Risk Force Deep Review
LowScripts Present
LowWeak Cryptodist/mcp/index.js
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to @omega3_0/nanoagent@2.1.16.
See all versions of @omega3_0/nanoagent for other recorded verdicts.
- Review the evidence and your use of @omega3_0/nanoagent@2.1.16 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.