AI agents invoke pcap_analyze to trigger actions in Zeek. 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.
This tool runs an external program (Zeek) to process/replay a PCAP file, which constitutes executing an external operation. It is not merely reading existing data — it actively triggers Zeek to process the file and generate new log artifacts.
From the tool's definition 'Replay a PCAP file through Zeek' — this triggers execution of Zeek against a PCAP file, running an external process/tool that generates log outputs. The description confirms it 'Creates connection, DNS, HTTP, SSL, and other logs' as side effects of execution.
Attacks that exploit this kind of access
Replay a PCAP file through Zeek and return the generated log summary. Creates connection, DNS, HTTP, SSL, and other logs from the packet capture. Useful for forensic analysis of captured traffic. It is categorised as a Execute tool in the Zeek MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Zeek MCP server in PolicyLayer and add a rule for pcap_analyze: 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 Zeek. Nothing to install.
pcap_analyze 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 pcap_analyze 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 pcap_analyze. 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.
pcap_analyze is provided by the Zeek MCP server (solomonneas/zeek-mcp). 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 →