AI agents call skill_correction_list to retrieve information from Llama without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries existing data (corrections/rules) without creating, modifying, deleting, or executing any operations. It is purely informational, similar to a GET request. The blast radius of misuse is minimal—an agent could only access metadata about skill corrections.
From the tool's definition Tool name contains 'list' and description states 'List the recorded corrections', indicating a retrieval/query operation with no side effects. Returns data about corrections/rules for a persona without modifying anything.
Attacks that exploit this kind of access
List the recorded corrections (long-term rules) for a persona/skill. These shape how. It is categorised as a Read tool in the Llama MCP Server, which means it retrieves data without modifying state.
Register the Llama MCP server in PolicyLayer and add a rule for skill_correction_list: 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 Llama. Nothing to install.
skill_correction_list 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 skill_correction_list 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 skill_correction_list. 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.
skill_correction_list is provided by the Llama MCP server (llama-ventures/llama-cli). 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 →