Download a skill directory from GitHub into a local folder.
AI agents use github_skills_install_skill to create or update resources in Agent Skills MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent Skills MCP environment.
The tool downloads and installs code/skill files locally, which is a Write operation that creates new data artifacts on the user's system. While it does not execute the skill code itself (that would be Execute), the installation modifies the local filesystem state.
From the tool's definition Tool description states 'Download a skill directory from GitHub into a local folder' — this creates or modifies local filesystem state by introducing new files/directories from an external source.
Attacks that exploit this kind of access
Download a skill directory from GitHub into a local folder. It is categorised as a Write tool in the Agent Skills MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agent Skills MCP server in PolicyLayer and add a rule for github_skills_install_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_install_skill 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 github_skills_install_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_install_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_install_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 →