convex_audit_functions
Audit all exported Convex functions for: missing validators (args/returns), old syntax usage, sensitive functions exposed publicly, and action-from-action anti-patterns. Scans all .ts files in the convex/ directory.
This record as markdown: /tools/io-github-homenshum-nodebench/convex-audit-functions.md
What convex_audit_functions does on Nodebench
AI agents call convex_audit_functions to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why convex_audit_functions is rated Low
This tool is a static analysis/auditing tool that examines code in the convex/ directory to identify potential security or code quality issues. It retrieves and analyzes information about exported functions without modifying them, executing arbitrary code, or causing destructive changes.
From the tool's definition Tool performs scanning and auditing of Convex functions ('Audit', 'Scans') to check for validators, syntax, and exposure patterns.
Attacks that exploit this kind of access
The rule that runs convex_audit_functions safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For convex_audit_functions, this is the rule to start with:
convex_audit_functions is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every convex_audit_functions call is checked against it from then on.
Questions about convex_audit_functions
Audit all exported Convex functions for: missing validators (args/returns), old syntax usage, sensitive functions exposed publicly, and action-from-action anti-patterns. Scans all .ts files in the convex/ directory. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.
Register the Nodebench MCP server in PolicyLayer and add a rule for convex_audit_functions: 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 Nodebench. Nothing to install.
convex_audit_functions 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 convex_audit_functions 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 convex_audit_functions. 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.
convex_audit_functions is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue