Manage skills on your LinkedIn profile.
AI agents use skills to create or update resources in LinkedIn MCP Pro Max — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LinkedIn MCP Pro Max environment.
Writing to a LinkedIn profile is a reversible modification that affects professional presentation and visibility. It is not a read-only query (Read), does not execute arbitrary code (Execute), and is not irreversible (Destructive). The impact is medium severity because skill modifications could influence job recommendations and recruiter searches, but are correctable by the user.
From the tool's definition Tool description states 'Manage skills on your LinkedIn profile' — the verb 'manage' indicates the ability to modify/update profile data.
Attacks that exploit this kind of access
Manage skills on your LinkedIn profile. It is categorised as a Write tool in the LinkedIn MCP Pro Max MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LinkedIn MCP Pro Max MCP server in PolicyLayer and add a rule for 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 MCP Pro Max. Nothing to install.
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 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 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.
skills is provided by the LinkedIn MCP Pro Max MCP server (mdnaimul22/linkedin-mcp-pro-max). 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 →