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 ...
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.
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…
Attacks that exploit this kind of access
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.
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.
metaharness_security_bench is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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.
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.
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.
metaharness_security_bench is one line of Ruflo's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →