AI agents use prepare_agent_session_log_upload to create or update resources in Hiring — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hiring environment.
This tool creates a new resource (a reserved upload slot) and stages data for writing to S3 storage, making it a Write operation. Severity is medium because session logs may contain sensitive personal information and application details, but the operation is reversible and does not directly access financial systems or destroy data.
From the tool's definition Tool 'prepare_agent_session_log_upload' reserves an upload slot for session logs (.tar.gz archives), which is a create/write operation that stores application conversation data.
Attacks that exploit this kind of access
Reserves an upload slot for the session log of THIS application conversation — a .tar.gz of the Claude. It is categorised as a Write tool in the Hiring MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Hiring MCP server in PolicyLayer and add a rule for prepare_agent_session_log_upload: 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 Hiring. Nothing to install.
prepare_agent_session_log_upload is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the prepare_agent_session_log_upload 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 prepare_agent_session_log_upload. 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.
prepare_agent_session_log_upload is provided by the Hiring MCP server (meetvaghani12/hiring_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 →