registry / aireceipts-cli / 0.9.0

aireceipts-cli@0.9.0

Your AI coding agent used millions of tokens. Here is the observable cost floor.

AI Security Review

scanned 21h ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

No blocking static signals were detected.

Trigger

User runs aireceipts, or explicitly runs `aireceipts install-hook` and confirms.

Impact

Creates local state and can add a persistent Claude Code hook; sends run metadata to telemetry.

Mechanism

AI-session reporting, opt-out telemetry, and confirmed Claude hook setup.

Rationale

This is not concrete malware: there are no lifecycle hooks and agent-config mutation requires an explicit confirmed command. The persistent agent-hook capability and default telemetry warrant a warning under the policy.

Evidence

package.jsondist/cli.jsdist/chunk-UCBOFRWI.jsdist/chunk-ES6XJOS2.jsdist/cli/commands/install-hook.js~/.claude/settings.json~/.claude/settings.json.bak~/.aireceipts/state.json~/.aireceipts/telemetry.json

Network endpoints1

eastus-8.in.applicationinsights.azure.com/v2/track

aireceipts-cli@0.9.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code