Rebuild the local OWASP database from upstream sources.
AI agents use update_database to create or update resources in Security Framework — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Security Framework environment.
This tool modifies the local OWASP database by refreshing it from upstream sources. While this is reversible (the database can be rebuilt again), it affects stored security reference data used by other tools on the server.
From the tool's definition The tool is named 'update_database' and described as 'Rebuild the local OWASP database from upstream sources.' The verb 'rebuild' indicates modification of data (the local database), which is a write operation.
Documented attack patterns abuse exactly the kind of access update_database gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Security Framework, and nothing reaches the server without passing your rules. This is the rule we recommend for update_database:
{
"version": "1",
"default": "deny",
"tools": {
"update_database": {
"limits": [
{
"counter": "update_database_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_database 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.
Rebuild the local OWASP database from upstream sources. It is categorised as a Write tool in the Security Framework MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Security Framework MCP server in PolicyLayer and add a rule for update_database: 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 Security Framework. Nothing to install.
update_database 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_database 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_database. 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_database is provided by the Security Framework MCP server (zer0-kr/security-framework-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Security Framework, 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.
41 Security Framework tools catalogued and risk-classified — across an index of 43,000+ MCP servers.