Post reputation feedback for another agent on Reputation Registry
AI agents use give_feedback to create or update resources in Waiaas — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Waiaas environment.
The tool writes/posts reputation feedback data to a registry, which is a reversible data modification (creating a new record). It does not delete, execute code, or move funds. However, it could be misused to manipulate agent reputation at scale, warranting medium severity.
From the tool's definition Post reputation feedback for another agent on Reputation Registry
Documented attack patterns abuse exactly the kind of access give_feedback gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Waiaas, and nothing reaches the server without passing your rules. This is the rule we recommend for give_feedback:
{
"version": "1",
"default": "deny",
"tools": {
"give_feedback": {
"limits": [
{
"counter": "give_feedback_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}give_feedback 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.
Post reputation feedback for another agent on Reputation Registry. It is categorised as a Write tool in the Waiaas MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Waiaas MCP server in PolicyLayer and add a rule for give_feedback: 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 Waiaas. Nothing to install.
give_feedback 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 give_feedback 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 give_feedback. 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.
give_feedback is provided by the Waiaas MCP server (minhoyoo-iotrust/waiaas). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Waiaas, 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.
126 Waiaas tools catalogued and risk-classified — across an index of 43,000+ MCP servers.