listTestFiles
AI agents call listTestFiles to retrieve information from BrowserStack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'list' prefix combined with context from sibling tools (which include write/execute operations like createTestCase, createTestRun) suggests this is a retrieval function. Listing files is a typical read operation that queries existing data without modification. Low severity because even if misused by an agent, it only exposes file metadata or names, not causing damage or data loss.
From the tool's definition Tool name 'listTestFiles' indicates it lists or retrieves test files. The description is empty, limiting certainty, but the name strongly suggests a query operation with no side effects.
Attacks that exploit this kind of access
listTestFiles. It is categorised as a Read tool in the BrowserStack MCP Server, which means it retrieves data without modifying state.
Register the BrowserStack MCP server in PolicyLayer and add a rule for listTestFiles: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches BrowserStack. Nothing to install.
listTestFiles is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the listTestFiles rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for listTestFiles. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
listTestFiles is provided by the BrowserStack MCP server (browserstack/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.