registry / @agentic-dev.ai/emo / 0.1.1
@agentic-dev.ai/emo@0.1.1
EMO by Agentic-dev: your own team of AI agents, on your computer, on your Claude subscription.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe reviewed execution and network paths align with the package’s stated agent and service-integration purpose. No install-time data collection or unrelated credential transfer was found; diagnostic reports are user-invoked and described in the tool interface.
Static reason
High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source
Trigger
The user runs the emo command or invokes an application tool; sending a problem report requires invoking the report tool.
Impact
No malicious impact identified. User-requested reports include diagnostic details and recent logs.
Mechanism
The package communicates with configured services, uses their corresponding credentials, and can send disclosed diagnostics to its licensing hub on request.
AI rationale
The reviewed execution and network paths align with the package’s stated agent and service-integration purpose. No install-time data collection or unrelated credential transfer was found; diagnostic reports are user-invoked and described in the tool interface.
Evidence
EMO_HOME/state/license.jsonEMO_HOME/outputs/דיווחים/<timestamp>.txtEMO_HOME/uploads/sumit/
Network endpoints4
api.sumit.co.ilwww.googleapis.comsecuretoken.googleapis.comfirestore.googleapis.com
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest has no install, preinstall, or postinstall hook; its scripts are for testing and building.
- The SUMIT connector sends configured account credentials to api.sumit.co.il, and document issuance requires owner approval.
- Problem reports are sent through a named tool that discloses the user words, system details, and recent logs; the report is saved locally and sent when invoked.
- The HTTP server binds to 127.0.0.1.
Evidence against
- Network access and credential use are consistent with the package’s configured service integrations.
- The report flow is described to users and is invoked through an explicit tool rather than automatically at install or startup.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
NoLicense
Source & flagged code
15 flaggedhub.jsonView file
4patternName = google_api_key
severity = high
line = 4
High
4patternName = google_api_key
severity = high
line = 4
High
bin/emo.mjsView file
8import path from 'node:path';
L9: import { spawn, spawnSync } from 'node:child_process';
L10: import { fileURLToPath } from 'node:url';
High
8
Findings
4 Critical8 High5 Medium6 Low
CriticalSame File Env Network Executionserver.mjs
CriticalHardcoded Runtime Data Exfiltrationmcp/sumit.mjs
CriticalCredential Exfiltrationserver.mjs
CriticalPrevious Version Dangerous Deltaserver.mjs
HighHigh Secrethub.json
HighChild Processbin/emo.mjs
HighShellserver.mjs
HighSandbox Evasion Gated Capabilityserver.mjs
HighTrigger Reachable Persistencebin/emo.mjs
HighShips High Entropy Blobpublic/models/hey_jarvis_v0.1.onnx
HighSemantic Analysis Limitedmcp/gmail.mjs#virtual:normalized:round1
HighSecret Patternhub.json
Affected versions and remediation
This report applies to @agentic-dev.ai/emo@0.1.1.
See all versions of @agentic-dev.ai/emo for other recorded verdicts.
- Review the evidence and your use of @agentic-dev.ai/emo@0.1.1 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.