AI agents call find_taint_paths 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.
Despite empty description, the tool operates within a static analysis knowledge graph (KuzuDB) for security auditing. It retrieves taint flow information without modifying code, executing external systems, or causing financial effects. The most severe action would be returning information that could inform a malicious agent, but the tool itself performs no side effects—it reads and reports.
From the tool's definition Tool name 'find_taint_paths' combined with server context describing 'multi-hop taint analysis' and 'call-flow tracing' indicates this tool queries the code knowledge graph to identify taint propagation routes.
Attacks that exploit this kind of access
find_taint_paths. 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_paths: 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_paths 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_paths 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_paths. 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_paths 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 →