Retrieve the full content (body + metadata) of a named skill.
AI agents call skills__get to retrieve information from SkillForge MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool fetches and returns skill data without creating, modifying, deleting, or executing anything. This is a pure read operation analogous to a GET request. The skill content itself may contain code, but retrieval and inspection do not constitute execution. Severity is low because reading skill metadata poses minimal risk; the actual execution would occur through the sibling tool 'skills__invoke'.
From the tool's definition Tool description states 'Retrieve the full content (body + metadata) of a named skill' — a retrieval operation with no modification or execution.
Attacks that exploit this kind of access
Retrieve the full content (body + metadata) of a named skill. It is categorised as a Read tool in the SkillForge MCP MCP Server, which means it retrieves data without modifying state.
Register the SkillForge MCP server in PolicyLayer and add a rule for skills__get: 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 SkillForge MCP. Nothing to install.
skills__get 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 skills__get 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__get. 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__get is provided by the SkillForge MCP server (lyupro/skillforge-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 →