AI agents call session_output to retrieve information from Pokeclaw without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves/reads existing session output and status information. It has no side effects — it does not modify, create, or delete anything. The severity is low because misuse only exposes logged output data from CLI sessions.
From the tool's definition "Get output from a session. Returns the full output log, current status, and exitCode."
Attacks that exploit this kind of access
Get output from a session. Returns the full output log, current status, and exitCode. An exited session with exitCode 0 completed successfully — read the output for the results. It is categorised as a Read tool in the Pokeclaw MCP Server, which means it retrieves data without modifying state.
Register the Pokeclaw MCP server in PolicyLayer and add a rule for session_output: 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 Pokeclaw. Nothing to install.
session_output 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 session_output 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 session_output. 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.
session_output is provided by the Pokeclaw MCP server (madebydia/pokeclaw). 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 →