mtech-ai-local-runner@0.1.87
D6 owner revision `fbc30fbe-cac9-45d1-9eff-bccec6ee6a54` selects a separate Gateway-initiated P2 verification budget: at most 1,500 weighted minutes per UTC calendar month and one active verification per workspace. This does not cap or certify the entire
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe manifest defines no install lifecycle hooks, and the CLI dispatches only on direct invocation. Agent integration writes are behind an explicit command, while the README’s reviewer-related wording is ordinary release context rather than a review instruction.
Decision evidence
public snapshot- The manifest has no install, preinstall or postinstall lifecycle scripts.
- The CLI calls its main function only when directly invoked.
- Agent hook installation is exposed through an explicit integrations install command and documented as request-only.
- Local tool policy excludes credentials, agent settings and other sensitive paths.
Source & flagged code
5 flaggedPackage text addresses the security reviewer or scanner and tries to influence the review outcome.
README.mdView on unpkgPackage source references dynamic require/import behavior.
dist/src/adapters/codex/pre-model-gate.jsView on unpkg · L31Findings
Affected versions and remediation
This report applies to mtech-ai-local-runner@0.1.87.
See all versions of mtech-ai-local-runner for other recorded verdicts.
- Review the evidence and your use of mtech-ai-local-runner@0.1.87 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.