AI agents call get_skill_summary 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 reports security audit information about GitHub repositories. It performs a lookup/query function to determine safety status, analogous to a database read or security check service. There are no side effects, data modifications, code execution, or irreversible operations.
From the tool's definition Tool description indicates it "Check[s] if a GitHub repository is safe" - a query/assessment action with no modification or execution capabilities. Returns security information about a repository without performing any actions on it.
Attacks that exploit this kind of access
Check if a GitHub repository is safe to install as an MCP server or AI agent skill. 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_skill_summary: 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_skill_summary 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_skill_summary 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_skill_summary. 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_skill_summary 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 →