AI agents call find_cross_service_taint to retrieve information from Orihime without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'find_' prefix and sibling analysis tools (find_cascade_risk, find_complexity_hints, find_eager_fetches) all perform static code analysis queries against the embedded KuzuDB index. This tool likely queries cross-service taint paths from the code graph without side effects. No evidence of code execution, data modification, deletion, or financial operations.
From the tool's definition Tool name 'find_cross_service_taint' uses 'find' verb, consistent with sibling tools (find_callees, find_callers, find_entry_points) which are query/search operations.
Attacks that exploit this kind of access
find_cross_service_taint. It is categorised as a Read tool in the Orihime MCP Server, which means it retrieves data without modifying state.
Register the Orihime MCP server in PolicyLayer and add a rule for find_cross_service_taint: 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 Orihime. Nothing to install.
find_cross_service_taint 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 find_cross_service_taint 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 find_cross_service_taint. 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.
find_cross_service_taint is provided by the Orihime MCP server (srinivasan-sundaresan95/orihime). 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 →