Google ADK runs generated code without a sandbox

HighAV-FW-019Runtime safetyFramework packNew in 2.0

What it finds

A Google ADK agent uses UnsafeLocalCodeExecutor to run model-written code on the host.

The executor is named "unsafe" for a reason: generated code runs with your app's full access.

What an attacker could do: Model-written code can read files, secrets and the network on the host.

Use BuiltInCodeExecutor or a container/VM-based executor with no secrets mounted.

Pro shows the corrected code for your exact file, step by step, and re-scans to confirm the fix. See plans

Finding code: GOOGLE_ADK_CODE_EXECUTOR_LOCAL
How it detects: Looks for a specific risky pattern in the code or config.
Confidence: Definite: the risky setting is written plainly in the file.
Scans: Agent source using the named framework (LangChain, CrewAI, AutoGen, OpenAI Agents SDK, Claude Agent SDK, computer-use tools)
OWASP LLM Top 10: LLM08 - Excessive Agency, LLM02 - Insecure Output Handling
NIST AI RMF: MG-2.2
SOC 2: CC6.8

Paste your agent code or MCP config. The free scan runs all 124 checks in about 10 seconds — no account needed.