Fetch the key files for a specific skill directory from GitHub.
AI agents call github_skills_get_skill to retrieve information from Agent Skills MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries skill file contents from GitHub repositories. It performs no create, modify, delete, or execute operations. The action is informational and reversible by design. Even in the context of skill discovery, fetching file contents is a standard read operation that poses minimal risk - the worst case is accessing unintended file contents, which is a low-severity read exposure.
From the tool's definition Tool description states 'Fetch the key files for a specific skill directory from GitHub' - a retrieval operation with no modification or execution capability.
Attacks that exploit this kind of access
Fetch the key files for a specific skill directory from GitHub. It is categorised as a Read tool in the Agent Skills MCP MCP Server, which means it retrieves data without modifying state.
Register the Agent Skills MCP server in PolicyLayer and add a rule for github_skills_get_skill: 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 Agent Skills MCP. Nothing to install.
github_skills_get_skill 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 github_skills_get_skill 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 github_skills_get_skill. 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.
github_skills_get_skill is provided by the Agent Skills MCP server (pinkpixel-dev/agentskills-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 →