New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

metaharness_security_bench

ADR-153 — upstream Darwin Shield (their own ADR-155): evolves a champion security-detection harness against a 10-vuln/9-decoy ground-truth corpus and grades on TPR/FPR/patch-pass/repro/unsafe vs four baselines (B0 static, B1 LLM-single-pass, B2 fixed-agent, B3 Darwin-champion). Closest reference ...

SERVERRuflo SOURCEruvnet/ruflo
High RISK CLASS
Category Execute
Parameters 00 required
Recommended Rate-limitedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/ruflo/metaharness-security-bench.md

What metaharness_security_bench does on Ruflo

AI agents invoke metaharness_security_bench to trigger actions in Ruflo. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Why metaharness_security_bench is rated High

This tool executes an automated, evolving security benchmark harness that runs code/agent workflows against a vulnerability corpus, evaluates detection and patching outcomes, and feeds results into a self-learning reward signal loop. It actively runs tests, spawns evaluations, and mutates/evolves a champion harness — all classic Execute-category behaviors.

From the tool's definition 'evolves a champion security-detection harness against a 10-vuln/9-decoy ground-truth corpus', 'grades on TPR/FPR/patch-pass/repro/unsafe vs four baselines', 'nightly self-learning security harness', 'running this periodically gives baseline diversity and…

Questions about metaharness_security_bench

What does the metaharness_security_bench tool do? +

ADR-153 — upstream Darwin Shield (their own ADR-155): evolves a champion security-detection harness against a 10-vuln/9-decoy ground-truth corpus and grades on TPR/FPR/patch-pass/repro/unsafe vs four baselines (B0 static, B1 LLM-single-pass, B2 fixed-agent, B3 Darwin-champion). Closest reference implementation for ruflo ADR-155 nightly self-learning security harness (#2417). Use when you need an empirical floor for Loop A reward-signal soundness; running this periodically gives baseline diversity and week-over-week champion-fitness drift. Bypassing this and just running the static MCP scan is wrong because static-only baseline (B0) reaches TPR=0.3/FPR=1 — proving static-alone has a measured detection ceiling. Parses overall PASS/FAIL + per-gate verdicts + baselines table from markdown. It is categorised as a Execute tool in the Ruflo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on metaharness_security_bench? +

Register the Ruflo MCP server in PolicyLayer and add a rule for metaharness_security_bench: 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 Ruflo. Nothing to install.

What risk level is metaharness_security_bench? +

metaharness_security_bench is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit metaharness_security_bench? +

Yes. Add a rate_limit block to the metaharness_security_bench 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.

How do I block metaharness_security_bench completely? +

Set action: deny in the PolicyLayer policy for metaharness_security_bench. 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.

What MCP server provides metaharness_security_bench? +

metaharness_security_bench is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Ruflo, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Ruflo's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.