Convert a PentesterFlow dataset to a specific training format. Handles Qwen tool roles, thinking blocks, and token limits.
AI agents use export_for_training to create or update resources in OffensiveSET — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OffensiveSET environment.
This tool writes/exports data by converting datasets into training-specific formats (e.g., Qwen tool roles, thinking blocks). While it processes existing data rather than deleting it, the conversion and export operations constitute write activities that create new data artifacts.
From the tool's definition Tool description states it "Convert[s] a PentesterFlow dataset to a specific training format," indicating data transformation and export operations that create or modify dataset outputs in new formats.
Documented attack patterns abuse exactly the kind of access export_for_training gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OffensiveSET, and nothing reaches the server without passing your rules. This is the rule we recommend for export_for_training:
{
"version": "1",
"default": "deny",
"tools": {
"export_for_training": {
"limits": [
{
"counter": "export_for_training_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}export_for_training stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Convert a PentesterFlow dataset to a specific training format. Handles Qwen tool roles, thinking blocks, and token limits. It is categorised as a Write tool in the OffensiveSET MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OffensiveSET MCP server in PolicyLayer and add a rule for export_for_training: 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 OffensiveSET. Nothing to install.
export_for_training 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 export_for_training 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 export_for_training. 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.
export_for_training is provided by the OffensiveSET MCP server (pentesterflow/offensiveset). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 OffensiveSET tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
10 OffensiveSET tools catalogued and risk-classified — across an index of 42,500+ MCP servers.