Acceptance testing for AI agents that take real actions. Show it a job once; it verifies your agent against the state of the system it changed.
- capability exposure inferred + 22
inferred
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 1w ago · see ecosystem CVEs →
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit 551676a · analyzer v33 · 1d ago
danger signals2
- suspicious endpoint 169.254.169.254 (cloud metadata) Konuktor-rigorrun-551676a/packages/agents/test/http.test.ts :86
expect(() => assertSafeAgentUrl('http://169.254.169.254/latest/meta-data/')).toThrow(); - suspicious endpoint 169.254.169.254 (cloud metadata) Konuktor-rigorrun-551676a/packages/mcp/test/safety.test.ts :35
expect(() => assertSafeMcpUrl('http://169.254.169.254/latest/meta-data/')).toThrow(
[](https://mcpobservatory.com/servers/github:Konuktor/rigorrun/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of Konuktor.