add_task_artifact
AI agents use add_task_artifact to create or update resources in Keshro MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Keshro MCP environment.
The tool appears to create or attach artifacts to tasks (reversible data modification), placing it in the Write category. Severity is medium due to the lack of a detailed description and uncertainty about what 'artifact' means in context—it could be metadata, files, or code artifacts.
From the tool's definition Tool name 'add_task_artifact' indicates it adds/creates artifacts associated with tasks. No description provided.
Attacks that exploit this kind of access
add_task_artifact. It is categorised as a Write tool in the Keshro MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Keshro MCP server in PolicyLayer and add a rule for add_task_artifact: 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 Keshro MCP. Nothing to install.
add_task_artifact 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 add_task_artifact 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 add_task_artifact. 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.
add_task_artifact is provided by the Keshro MCP server (jlewitt1/keshro-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 →