Lookup CVE details
AI agents call cve_lookup to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries existing CVE (Common Vulnerabilities and Exposures) data with no side effects, modification, code execution, or data destruction. It is a straightforward read operation. Severity is low because the tool itself does not introduce risk; it only returns informational data about known vulnerabilities that are already public knowledge.
From the tool's definition Tool name is 'cve_lookup' with description 'Lookup CVE details'. The verb 'Lookup' and 'cve_lookup' both indicate a read-only query operation that retrieves vulnerability information from a database or external source.
Attacks that exploit this kind of access
Lookup CVE details. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for cve_lookup: 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 Claude Flow. Nothing to install.
cve_lookup 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 cve_lookup 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 cve_lookup. 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.
cve_lookup is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.