registry / gitgecko / 0.1.6

gitgecko@0.1.6

GitGecko - agent-native code review and code intelligence.

AI Security Review

scanned 1h ago · by lpm-firewall-ai

No confirmed malicious attack surface. The user-invoked CLI reads review context and invokes selected local agents or configured provider/cloud endpoints; it persists GitGecko-owned state.

Static reason

High-risk behavior combination matched malicious policy.

Trigger

User runs `gitgecko review`, `login`, model configuration, or thread commands.

Impact

Review content and configured provider credentials are used only in the requested provider/auth workflow.

Mechanism

User-directed code-review CLI with optional local-agent and model-provider integrations.

Rationale

Static inspection shows a feature-aligned, explicitly invoked code-review CLI rather than install-time or stealthy malicious behavior. Scanner findings arise from bundled agent/provider functionality and do not establish an attack chain.

Evidence

package.jsondist/gitgecko.jsREADME.md~/gitgecko/auth.json~/gitgecko/config.json~/gitgecko/threads/v1

Network endpoints2

app.gitgecko.comgitgecko.com

Decision evidence

public snapshot

AI called this Clean at 91.0% confidence as with false-positive risk.

gitgecko@0.1.6

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Behavioral surface

Source & flagged code