Return a skill-routing manifest with workflow phases, recommended tool sequence, skill activation order, quality gates, required outputs, instructions, and disallowed actions.
AI agents call route_skills to retrieve information from CodeAudit MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and returns a structured routing manifest. It is purely informational/advisory, generating a plan artifact with no side effects. The server itself is described as 'read-only', further supporting a Read classification with low severity.
From the tool's definition 'Return a skill-routing manifest' — the tool produces a manifest/plan document describing workflow phases, tool sequences, and instructions without modifying any data or executing any commands.
Attacks that exploit this kind of access
Return a skill-routing manifest with workflow phases, recommended tool sequence, skill activation order, quality gates, required outputs, instructions, and disallowed actions. It is categorised as a Read tool in the CodeAudit MCP MCP Server, which means it retrieves data without modifying state.
Register the CodeAudit MCP server in PolicyLayer and add a rule for route_skills: 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 CodeAudit MCP. Nothing to install.
route_skills 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 route_skills 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 route_skills. 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.
route_skills is provided by the CodeAudit MCP server (priyanshuchawda/codeaudit). 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 →