AI agents use create_finding to create or update resources in Reptor — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Reptor environment.
The tool creates (not reads) data in a pentest reporting system. While reversible (distinguishing it from Destructive), this is a Write operation that introduces new structured data into a security assessment workflow. Severity is high because erroneous or malicious findings in a pentest report could mislead security decisions, inflate risk assessments, or damage client trust.
From the tool's definition Tool name 'create_finding' indicates creation of a new record. Server purpose is 'pentest reporting and automation' managing 'findings, projects, and templates.' Creating findings in a pentest report system modifies reportable data and can affect downstream…
Documented attack patterns abuse exactly the kind of access create_finding gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Reptor, and nothing reaches the server without passing your rules. This is the rule we recommend for create_finding:
{
"version": "1",
"default": "deny",
"tools": {
"create_finding": {
"limits": [
{
"counter": "create_finding_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_finding 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.
create_finding. It is categorised as a Write tool in the Reptor MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Reptor MCP server in PolicyLayer and add a rule for create_finding: 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 Reptor. Nothing to install.
create_finding 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 create_finding 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 create_finding. 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.
create_finding is provided by the Reptor MCP server (slvnlrt/reptor-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Reptor, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Reptor tools catalogued and risk-classified — across an index of 43,000+ MCP servers.