Sangfor 매뉴얼/가이드 검색
AI agents call search_manuals to retrieve information from Sangfor Mcp Workflow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches existing manuals and guides without modifying, executing code, or triggering external state changes. It is a pure read operation with no side effects, making it low-severity even in adversarial use—worst case an agent retrieves irrelevant documentation.
From the tool's definition Tool name 'search_manuals' and description 'Sangfor 매뉴얼/가이드 검색' (Sangfor manual/guide search) clearly indicate a retrieval/query operation over documentation.
Attacks that exploit this kind of access
Sangfor 매뉴얼/가이드 검색. It is categorised as a Read tool in the Sangfor Mcp Workflow MCP Server, which means it retrieves data without modifying state.
Register the Sangfor Mcp Workflow MCP server in PolicyLayer and add a rule for search_manuals: 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 Sangfor Mcp Workflow. Nothing to install.
search_manuals 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 search_manuals 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 search_manuals. 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.
search_manuals is provided by the Sangfor Mcp Workflow MCP server (whelp99-code/sangfor-mcp-workflow). 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 →