Google Stitch MCP

• Outcome: Pass
• Latest audit: Sep 15, 2026 · 1:43 AM UTC
• Version: 1.0.0

Overview

This skill is a straightforward guide for using Google Stitch's remote MCP API, with network calls and API-key use disclosed and aligned with its purpose.

Install this only if you intend to let your agent call Google Stitch with your Stitch API key. Keep the API key private, avoid sending sensitive prompts or project data unless appropriate for Google Stitch, and remove the MCP client entry or rotate the key when you no longer need access.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 60% confidence

Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

Stitch exposes a standard MCP HTTP endpoint. To call a tool, POST to the MCP endpoint with the tool name and arguments.

bash

curl -X POST https://stitch.googleapis.com/mcp \
  -H "Content-Type: application/json" \
  -H "X-Goog-Api-Key: YOUR_STITCH_API_KEY" \
  -d '{

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 60% confidence

Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 131)May include surrounding context.

• If output_components has suggestions, present them to user. If accepted, call again with the suggestion as the new prompt.

bash

curl -X POST https://stitch.googleapis.com/mcp \
  -H "Content-Type: application/json" \
  -H "X-Goog-Api-Key: YOUR_STITCH_API_KEY" \
  -d '{

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 70% confidence

Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 245)May include surrounding context.

md

"method": "tools/call",
        "params": {"name": tool_name, "arguments": args}
    }
    r = requests.post(MCP_URL, headers=HEADERS, json=payload)
    r.raise_for_status()
    return r.json()

Static analysis

No suspicious patterns detected.