Update the skills list (max 50).
AI agents use update_skills to create or update resources in LinkedIn Profile MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LinkedIn Profile MCP Server environment.
The tool creates or modifies data reversibly by updating a user's skills section on LinkedIn. While this is a profile modification, it is not destructive (skills can be edited/removed later) and does not delete or irreversibly alter data.
From the tool's definition Tool description explicitly states 'Update the skills list', which is a modification operation. The context indicates this modifies LinkedIn profile content via 'real-time API access' to manage 'professional content'.
Attacks that exploit this kind of access
Update the skills list (max 50). It is categorised as a Write tool in the LinkedIn Profile MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LinkedIn Profile MCP Server MCP server in PolicyLayer and add a rule for update_skills: 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 LinkedIn Profile MCP Server. Nothing to install.
update_skills 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 update_skills 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 update_skills. 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.
update_skills is provided by the LinkedIn Profile MCP Server MCP server (thejosem4/linkedin-profile-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 →