AI agents call confluence_get_attachment_image to retrieve information from Atlassian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves image data from a Confluence page attachment. It performs a read-only operation with no side effects on the underlying data. There is no creation, modification, deletion, code execution, or financial impact. The low severity reflects minimal blast radius—retrieving an image cannot harm systems or cause unintended consequences.
From the tool's definition Tool name contains 'get' and description states 'Gets an image attachment' and 'returns it as an Image', indicating retrieval without modification.
Attacks that exploit this kind of access
Gets an image attachment on a Confluence page and returns it as an Image. It is categorised as a Read tool in the Atlassian MCP Server, which means it retrieves data without modifying state.
Register the Atlassian MCP server in PolicyLayer and add a rule for confluence_get_attachment_image: 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 Atlassian. Nothing to install.
confluence_get_attachment_image 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 confluence_get_attachment_image 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 confluence_get_attachment_image. 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.
confluence_get_attachment_image is provided by the Atlassian MCP server (tingyiy/atlassian-mcp-server). 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 →