mt_skill_audit
AI agents call mt_skill_audit to retrieve information from MolTrust MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the trust infrastructure context (DIDs, reputation, credentials) and the 'audit' nomenclature, this tool most likely performs a read-only inspection or query of skill-related data or agent capabilities. Without a description, confidence is reduced, but the audit pattern consistently maps to Read operations across security domains. Severity is low since read operations have minimal blast radius.
From the tool's definition Tool name 'mt_skill_audit' suggests an audit or inspection function. The 'audit' component typically implies reading/querying state rather than modification. No description provided to confirm.
Attacks that exploit this kind of access
mt_skill_audit. It is categorised as a Read tool in the MolTrust MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MolTrust MCP Server MCP server in PolicyLayer and add a rule for mt_skill_audit: 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 MolTrust MCP Server. Nothing to install.
mt_skill_audit 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 mt_skill_audit 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 mt_skill_audit. 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.
mt_skill_audit is provided by the MolTrust MCP Server MCP server (pypi:moltrust-mcp-server). 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 →