Scan an AI agent skill, plugin, or MCP server for security risks.
AI agents call prism_scan 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.
A security scan reads and analyzes the target artifact without modifying or destroying it. The output is a report of findings. However, severity is medium because scanning could involve executing or probing the target in ways that have side effects; the description is vague enough to allow for active probing.
From the tool's definition 'Scan an AI agent skill, plugin, or MCP server for security risks' — scanning/analysis operation that reads and evaluates a target for risks
Attacks that exploit this kind of access
Scan an AI agent skill, plugin, or MCP server for security risks. 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_scan: 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_scan 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_scan 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_scan. 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_scan 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 →