AI agents use update_project to create or update resources in Keyshade — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Keyshade environment.
The tool modifies project configuration data without permanently destroying it (distinguishing it from Destructive category). It is reversible through subsequent updates. Severity is high because unauthorized project updates in a secrets management system could alter access controls, configurations, or secret associations, affecting multiple secrets and users depending on that project.
From the tool's definition Tool name 'update_project' and description 'Updates a project' indicate modification of existing data. Context shows this is part of a secrets management platform (Keyshade) where projects are configuration entities.
Documented attack patterns abuse exactly the kind of access update_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Keyshade, and nothing reaches the server without passing your rules. This is the rule we recommend for update_project:
{
"version": "1",
"default": "deny",
"tools": {
"update_project": {
"limits": [
{
"counter": "update_project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_project stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Updates a project. It is categorised as a Write tool in the Keyshade MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Keyshade MCP server in PolicyLayer and add a rule for update_project: 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 Keyshade. Nothing to install.
update_project 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 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. 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 is provided by the Keyshade MCP server (keyshade-xyz/keyshade-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Keyshade, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
44 Keyshade tools catalogued and risk-classified — across an index of 43,000+ MCP servers.