Update a custom project role.
AI agents use update_project_role to create or update resources in Infisical MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Infisical MCP environment.
This tool modifies role configurations reversibly rather than deleting them, placing it in the Write category. Severity is high because misconfiguring project roles could grant unintended permissions to users or restrict legitimate access, affecting multiple users and potentially sensitive operations. The Infisical context (secrets management system) amplifies the blast radius of role misconfigurations.
From the tool's definition Tool description states 'Update a custom project role,' which modifies existing role definitions. The server description confirms it exposes tools to 'update' projects, environments, folders, and secrets.
Attacks that exploit this kind of access
Update a custom project role. It is categorised as a Write tool in the Infisical MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Infisical MCP server in PolicyLayer and add a rule for update_project_role: 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 Infisical MCP. Nothing to install.
update_project_role is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_project_role 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 update_project_role. 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.
update_project_role is provided by the Infisical MCP server (plgonzalezrx8/infisicalmcp). 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 →