Automatically escalate priority for aged issues. P3→P2 after 30 days, P2→P1 after 14 days, P1→P0 after 3 days. Security issues are always P0.
AI agents call gitea_workflow_escalate_priority to retrieve information from Gitea MCP Tool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though gitea_workflow_escalate_priority only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Automatically escalate priority for aged issues. P3→P2 after 30 days, P2→P1 after 14 days, P1→P0 after 3 days. Security issues are always P0. It is categorised as a Read tool in the Gitea MCP Tool MCP Server, which means it retrieves data without modifying state.
Register the Gitea MCP Tool MCP server in PolicyLayer and add a rule for gitea_workflow_escalate_priority: 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 Gitea MCP Tool. Nothing to install.
gitea_workflow_escalate_priority 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 gitea_workflow_escalate_priority 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 gitea_workflow_escalate_priority. 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.
gitea_workflow_escalate_priority is provided by the Gitea MCP Tool MCP server (supenbysz/gitea-mcp-tool). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.