linux_yara_scan
AI agents invoke linux_yara_scan to trigger actions in Velociraptor MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
A YARA scan executes pattern-matching rules against files or memory on a Linux system. While it is primarily a read/scan operation, running arbitrary YARA rules across a system constitutes executing an operation with potentially broad system access.
From the tool's definition Tool name 'linux_yara_scan' on a server designed for 'file/memory scans, remediation actions, and artifact collection'. Sibling tools include 'collect_artifact', 'kill_process', 'hunt_across_fleet'.
Attacks that exploit this kind of access
linux_yara_scan. It is categorised as a Execute tool in the Velociraptor MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Velociraptor MCP Server MCP server in PolicyLayer and add a rule for linux_yara_scan: 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 Velociraptor MCP Server. Nothing to install.
linux_yara_scan is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the linux_yara_scan 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 linux_yara_scan. 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.
linux_yara_scan is provided by the Velociraptor MCP Server MCP server (snoe-findley/mcp-velociraptor). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →