AI agents call get_skill_instructions to retrieve information from Eff without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays instructional content about the Ethics Filter Framework skill. It performs a read-only operation that retrieves information without any side effects, data modification, code execution, or irreversible actions. The severity is low because accessing skill instructions poses minimal risk regardless of how an AI agent uses it.
From the tool's definition Tool description states 'Return the EFF skill instructions and workflow' - uses 'Return' which indicates data retrieval with no modification. The tool fetches documentation/instructions from an internal resource (eff://skill) and presents them to the user.
Attacks that exploit this kind of access
Return the EFF skill instructions and workflow (eff://skill). It is categorised as a Read tool in the Eff MCP Server, which means it retrieves data without modifying state.
Register the Eff MCP server in PolicyLayer and add a rule for get_skill_instructions: 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 Eff. Nothing to install.
get_skill_instructions 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 get_skill_instructions 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 get_skill_instructions. 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.
get_skill_instructions is provided by the Eff MCP server (vs3kulic/eff-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 →