registry / ask-gemini-mcp / 1.6.13

ask-gemini-mcp@1.6.13

Moved to @ask-llm/gemini-mcp. The ask-gemini-mcp executable name is unchanged.

MCP server for Gemini CLI integration - for Claude IDE and other IDEs

AI Security Review

scanned 20h 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

Starting the MCP server and invoking ask-gemini or ask-gemini-edit.

Impact

A host AI agent can cause an unsandboxed external CLI to inspect or act in the current workspace; prompts and edit chunks may be cached temporarily.

Mechanism

Agent-invoked Gemini CLI execution with default workspace-trust bypass.

Rationale

No concrete malicious install-time behavior, exfiltration, persistence, or foreign agent-config mutation was found. Warn because runtime operation deliberately enables a trusted, potentially unsandboxed external AI CLI in the workspace.

Evidence

package.jsondist/index.jsdist/tools-BnFFDjm2.jsdist/geminiExecutor-BeigwopC.jsREADME.md/tmp/gemini-mcp-chunks/*.json

Decision evidence

public snapshot

AI called this Suspicious at 87.0% confidence as Dangerous Capability with low false-positive risk.

Evidence for warning

ask-gemini-mcp@1.6.13

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code