AI agents call find_taint_sinks 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 tool name pattern and server context (code knowledge graph with KuzuDB) indicate this retrieves or identifies locations where taint flows terminate in the code, supporting static analysis workflows. This is information retrieval with no side effects on the codebase itself.
From the tool's definition Tool name 'find_taint_sinks' suggests querying/locating code locations; sibling tools on this server (find_callees, find_callers, find_entry_points, find_cascade_risk) are all query/analysis tools that retrieve information from the code graph.
Attacks that exploit this kind of access
find_taint_sinks. 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_taint_sinks: 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_taint_sinks 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_taint_sinks 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_taint_sinks. 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_taint_sinks 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 →