linux_pslist
AI agents call linux_pslist to retrieve information from Velociraptor MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Process listing (pslist) is a read-only operation that retrieves running process information without modifying system state. However, severity is medium rather than low because in a forensics/incident response context, detailed process information could expose sensitive operational details or aid in lateral movement if misused by a compromised agent.
From the tool's definition Tool name 'linux_pslist' indicates process listing functionality (reading process information), consistent with sibling tools like 'client_info' and 'collect_artifact' that perform information gathering.
Attacks that exploit this kind of access
linux_pslist. It is categorised as a Read tool in the Velociraptor MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Velociraptor MCP Server MCP server in PolicyLayer and add a rule for linux_pslist: 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_pslist 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 linux_pslist 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_pslist. 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_pslist 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 →