AI agents call find_second_order_injection 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 appears to be a taint analysis search tool that identifies second-order injection vulnerabilities in code (a common static analysis operation). It follows the naming pattern of sibling analysis tools that query and trace code flows without modifying state. The 'find_*' prefix strongly suggests this performs reads against the embedded KuzuDB rather than executing code or modifying data.
From the tool's definition Tool name is 'find_second_order_injection', which contains the verb 'find' indicating a search/query operation.
Attacks that exploit this kind of access
find_second_order_injection. 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_second_order_injection: 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_second_order_injection 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_second_order_injection 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_second_order_injection. 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_second_order_injection 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 →