AI agents use report_ablegen to create or update resources in Lokyy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lokyy environment.
The tool writes a new report file to a designated output directory using a date-based naming convention. It creates data persistently but does not delete, execute code, or involve finances. Severity is medium because it writes structured files to the filesystem and could be misused to store large volumes of data or overwrite existing reports if naming collides.
From the tool's definition 'Legt einen Frage-Report' (creates/stores a question report) and specifies an output path 'nach Outputs/' with a defined naming schema — this is a file creation/write operation.
Attacks that exploit this kind of access
Legt einen Frage-Report nach Outputs/ (Namensschema JJJJ-MM-TT_frage-kurzform.md). Verweigert [[Verweise]] — Reports nutzen Klartext-Namen. It is categorised as a Write tool in the Lokyy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lokyy MCP server in PolicyLayer and add a rule for report_ablegen: 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 Lokyy. Nothing to install.
report_ablegen 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 report_ablegen 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 report_ablegen. 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.
report_ablegen is provided by the Lokyy MCP server (oliverhees/lokyy-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 →