@agentic-dev.ai/emo@0.1.13
EMO by Agentic-dev: your own team of AI agents, on your computer, on your Claude subscription.
AI Security Review
scanned 4d ago · by lpm-firewall-aiThis is a user-run AI command center with no install hook, but it enables identifiable activity telemetry by default after hub sign-in. The payload is limited to metadata and goes to the product's own service, so this warrants a warning rather than a publish block.
Decision evidence
public snapshot- After hub sign-in, the activity reporter is enabled for licensed, non-development installs by default; no opt-out check appears in this gate.
- The reporter starts automatically on a two-minute interval.
- It sends heartbeat counts and version data to Firestore under the signed-in user's account.
- Per-run events include agent ID and name, action kind and status, duration, token count, and tool-category counts.
- package.json has no install, preinstall, or postinstall script.
- The reporter sends a bounded metadata record; the inspected event fields do not include prompts, messages, tool arguments, or results.
- The external reporting destination is the product's own Firebase Firestore service; no unrelated collector was identified in this flow.
Source & flagged code
15 flaggedFindings
Affected versions and remediation
This report applies to @agentic-dev.ai/emo@0.1.13.
See all versions of @agentic-dev.ai/emo for other recorded verdicts.
- Review the evidence and your use of @agentic-dev.ai/emo@0.1.13 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.