registry / ask-gemini-mcp / 1.6.14

ask-gemini-mcp@1.6.14

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 17h ago · by lpm-firewall-ai

No confirmed malicious attack surface. At runtime, user-invoked MCP tools delegate prompts to the locally installed Gemini CLI; temporary edit chunks are cached locally.

Static reason

No blocking static signals were detected.; previous stored version diff introduced dangerous source

Trigger

User or MCP client invokes ask-gemini, ask-gemini-edit, fetch-chunk, or ping.

Impact

The intended Gemini CLI invocation may read user-requested workspace files; no covert exfiltration or persistence is implemented.

Mechanism

Stdio MCP server spawning Gemini CLI with validated tool arguments.

Rationale

The package has no install-time execution or agent-config mutation. Its process spawning and workspace-trust flags support its explicit, user-invoked Gemini MCP function and do not form a concrete malicious chain.

Evidence

package.jsondist/cli.jsdist/index.jsdist/tools-BHe5UEbr.jsdist/geminiExecutor-C4FX6KIs.jsREADME.md

Decision evidence

public snapshot

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

Evidence for block

Runtime sets Gemini workspace-trust environment flags.

ask-gemini-mcp@1.6.14

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code