AI agents call get_audit_report to retrieve information from Oathe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns audit report data without creating, modifying, deleting, or executing anything. It is purely informational - a Read operation. Severity is low because retrieving audit reports poses minimal risk; the worst case is information disclosure of audit metadata, which is non-destructive and typically intended to be shared.
From the tool's definition Tool description states 'Get the full behavioral security audit report' - a retrieval operation. The action is passive data retrieval with no modification, deletion, or execution of code. It queries and returns audit information about a GitHub repository.
Attacks that exploit this kind of access
Get the full behavioral security audit report for a GitHub repository. It is categorised as a Read tool in the Oathe MCP Server, which means it retrieves data without modifying state.
Register the Oathe MCP server in PolicyLayer and add a rule for get_audit_report: 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 Oathe. Nothing to install.
get_audit_report 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 get_audit_report 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 get_audit_report. 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.
get_audit_report is provided by the Oathe MCP server (oathe-ai/oathe-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 →