Generate a cleanup plan for system residue found by prism_clean_scan.
AI agents call prism_clean_plan to retrieve information from Prism Scanner without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool generates a cleanup plan (a report or recommendation), which is a read/query-style operation producing output without modifying or deleting anything. The actual cleanup would be a separate step. Severity is low since misuse would at most surface inaccurate recommendations, not cause direct harm.
From the tool's definition Generate a cleanup plan — this produces a plan/report based on scan findings, no indication of executing or applying changes
Attacks that exploit this kind of access
Generate a cleanup plan for system residue found by prism_clean_scan. It is categorised as a Read tool in the Prism Scanner MCP Server, which means it retrieves data without modifying state.
Register the Prism Scanner MCP server in PolicyLayer and add a rule for prism_clean_plan: 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 Prism Scanner. Nothing to install.
prism_clean_plan 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 prism_clean_plan 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 prism_clean_plan. 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.
prism_clean_plan is provided by the Prism Scanner MCP server (aidongise-cell/prism-scanner). 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 →