AI agents call snow_sanitize_input to retrieve information from Serac without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a defensive utility that reads/transforms input strings to escape potentially dangerous characters. It does not retrieve data, modify records, execute code, delete anything, or commit financial transactions. The note about preferring parameterized queries confirms this is a secondary defensive measure, not a primary operation.
From the tool's definition Tool name 'snow_sanitize_input' and description 'Escape a user-supplied string against html, sql, or script-injection contexts' indicate a data sanitization utility.
Attacks that exploit this kind of access
Escape a user-supplied string against html, sql, or script-injection contexts. Note: prefer parameterized queries for SQL — sanitization is a fallback, not the primary defense. It is categorised as a Read tool in the Serac MCP Server, which means it retrieves data without modifying state.
Register the Serac MCP server in PolicyLayer and add a rule for snow_sanitize_input: 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 Serac. Nothing to install.
snow_sanitize_input 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 snow_sanitize_input 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 snow_sanitize_input. 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.
snow_sanitize_input is provided by the Serac MCP server (serac-labs/serac). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
snow_sanitize_input is one line of Serac's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →