List the 100 most recent Harden-Runner-monitored workflow runs for a GitHub organization, optionally narrowed to one repository. Use this to discover run IDs when the user asks about a run without giving an explicit ID — e.g.
AI agents call list_recent_workflow_runs to retrieve information from Stepsecurity without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though list_recent_workflow_runs 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
List the 100 most recent Harden-Runner-monitored workflow runs for a GitHub organization, optionally narrowed to one repository. Use this to discover run IDs when the user asks about a run without giving an explicit ID — e.g. It is categorised as a Read tool in the Stepsecurity MCP Server, which means it retrieves data without modifying state.
Register the Stepsecurity MCP server in PolicyLayer and add a rule for list_recent_workflow_runs: 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 Stepsecurity. Nothing to install.
list_recent_workflow_runs 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_recent_workflow_runs 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_recent_workflow_runs. 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_recent_workflow_runs is provided by the Stepsecurity MCP server (step-security/stepsecurity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.