@cakagus/codeclaw@1.2.1
AI agent terminal + Telegram bot untuk coding, trading, dan research — dengan skill system auto-upgrade.
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe reviewed findings resolve to ordinary CodeClaw functionality: configured API keys are used for market research and Telegram delivery, and the flagged script does not execute its main routine on import. The package manifest has no lifecycle hooks, and doctor fixes are opt-in.
Decision evidence
public snapshot- The manifest declares no install, preinstall, or postinstall hook; its scripts are user-invoked commands.
- The gold analysis script reads API keys and Telegram settings from config.json, then uses them for the corresponding data and messaging features.
- The gold analysis script runs its main routine only when invoked directly, not when imported.
- Telegram notifications require a configured bot token and chat ID.
- The package includes network access, credential handling, and filesystem writes, but the reviewed flows serve the advertised research and Telegram features.
- The doctor command’s fixes are selected through the explicit --fix option.
Source & flagged code
6 flaggedPackage source references dynamic require/import behavior.
bin/codeclaw.jsView on unpkg · L17This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
lib/doctor.jsView on unpkgSource writes installer persistence such as shell profile or service configuration.
lib/doctor.jsView on unpkg · L2Source sends credentials or rich application records to a package-controlled external receiver enabled by default.
scripts/gold-analysis.mjs#virtual:normalized:round1View on unpkg · L55Package ships non-JavaScript build or shell helper files.
bin/tokenobral-deploy.shView on unpkgA bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
lib/research.js#virtual:normalized:round1View on unpkgFindings
Affected versions and remediation
This report applies to @cakagus/codeclaw@1.2.1.
See all versions of @cakagus/codeclaw for other recorded verdicts.
- Review the evidence and your use of @cakagus/codeclaw@1.2.1 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.