AI agents call list_sources to retrieve information from Llm Wiki without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only lists or queries existing ingested sources within a wiki—a read-only operation with no side effects. It retrieves information but does not create, modify, delete, or execute any operations. The severity is low because even if misused by an agent, it only exposes metadata about wiki structure and contents, posing minimal risk.
From the tool's definition Tool name 'list_sources' and description '列出指定 wiki 中已经 ingest 过的所有原始文件' (List all raw files that have been ingested in the specified wiki) indicates a retrieval/query operation that returns metadata about ingested sources without modifying or deleting data.
Attacks that exploit this kind of access
列出指定 wiki 中已经 ingest 过的所有原始文件。. It is categorised as a Read tool in the Llm Wiki MCP Server, which means it retrieves data without modifying state.
Register the Llm Wiki MCP server in PolicyLayer and add a rule for list_sources: 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 Llm Wiki. Nothing to install.
list_sources 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 list_sources 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 list_sources. 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.
list_sources is provided by the Llm Wiki MCP server (quick-sort/llm-wiki-mcp). 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 →