Openapi Graph
OpenAPI front example; a graph whose step turns an OpenAPI operation into a sealed tool result.
Install
$ agentstack add skill-runxhq-runx-openapi-graph ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-runxhq-runx-openapi-graph) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
OpenAPI graph
A single-step graph that drives the OpenAPI external-adapter sub-skill. The runtime routes the graph step's external-adapter source through the source-adapter registry to the external-adapter executor, which spawns the declared adapter process. The adapter resolves an OpenAPI operation into a concrete HTTP request and the runtime seals it. Its manifest declares a network sandbox intent because the adapter performs the outbound fetch.
This is the concrete proof that the core runs from other specs, not just MCP. Run examples/openapi-graph/run.sh to start the local fixture endpoint and fail hard unless the graph state proves the GET executed and returned the expected pet payload, and the receipt directory contains a signed runx.receipt.v1.
The inline harness case expects that fixture endpoint to be running. Use run.sh for the hermetic demo entrypoint; bare runx harness examples/openapi-graph is only useful after starting server.mjs separately.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: runxhq
- Source: runxhq/runx
- License: MIT
- Homepage: https://runx.ai
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.