AI agents use knitbrain_compose_skill to create or update resources in Knitbrain — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Knitbrain environment.
The tool creates a new skill entry (Write), as indicated by 'Compose a NEW project-tailored skill'. This is a reversible data creation operation stored in the local-first memory system. Misuse could lead to polluted or malicious skill definitions influencing AI agent behavior, hence medium severity.
From the tool's definition Compose a NEW project-tailored skill for a task
Attacks that exploit this kind of access
Compose a NEW project-tailored skill for a task in the USER. It is categorised as a Write tool in the Knitbrain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Knitbrain MCP server in PolicyLayer and add a rule for knitbrain_compose_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 Knitbrain. Nothing to install.
knitbrain_compose_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 knitbrain_compose_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 knitbrain_compose_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.
knitbrain_compose_skill is provided by the Knitbrain MCP server (pdgit12/knitbrain). 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 →