T09 · Insecure Skill Coding Practices
Error
- Location
scripts/evaluation.py:83- Finding
Evaluation Harness Does Not Enforce Read-Only Tool Execution
- Content
View full analysis
tuple[str, dict[str, Any]]: """Run the agent loop with MCP tools.""" messages = [{"role": "user", "content": question}] response = await asyncio.to_thread( client.messages.create, model=model, max_tokens=4096, system=EVALUATION_PROMPT, messages=messages, tools=tools, ) messages.append({"role": "assistant", "content": response.content}) tool_metrics = {} while response.stop_reason == "tool_use": tool_use = next(block for block in response.content if block.type == "tool_use") tool_name = tool_use.name tool_input = tool_use.input tool_start_ts = time.time() try: tool_result = await connection.call_tool(tool_name, tool_input) tool_response = json.dumps(tool_result) if isinstance(tool_result, (dict, list)) else str(tool_result) except Exception as e: tool_response = f"Error executing tool {tool_name}: {str(e)}\n" tool_response += traceback.format_exc() ``` The connection layer also strips MCP behavioral annotations when exposing tools: ```python async def list_tools(self) -> list[dict[str, Any]]: """Retrieve available tools from the MCP server.""" response = await self.session.list_tools() return [ { "name": tool.name, "description": tool.description, "input_schema": tool.inputSchema, } for tool in response.tools ] async def call_tool(self, tool_name: str, arguments: dict[str, Any]) -> Any: ...[truncated 2051 chars]- Remediation
View remediation