.claude/skills/danubeRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Governed tool access for AI agents — one Danube API key unlocks your organization's own tools plus a large, growing catalog of services, over MCP or curl, with confirmation before anything that writes, sends, spends, or deletes.
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/danubeRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/danubeRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/danubeRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @danube/tools-marketplaceclawhub inspect @danube/tools-marketplace --version 8.1.5This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:9fdc7f7368e4d91b4bfcd247c9a313d2274a56558b0289f0a04d6d45202d2c11agents/danube-icon.pngagents/openai.yamlreferences/rest-api.mdreferences/troubleshooting.mdskill-card.mdSKILL.mdDocuments four live behaviours the skill had never mentioned, each of which an agent following 8.1.4 would have misread — three of them as a failure that wasn't one. - **The free-tier cap on AI-powered workflows.** A free-tier account gets 5 lifetime *successful* workflow runs that use a Danube-hosted AI step; past that, `execute_workflow` refuses the run with HTTP `402` before any step executes, so nothing partially ran and no execution row exists. The skill said nothing about `402`. Worse, `402` isn't in the backend's status→code map, so the error envelope's `code` reads `internal_error` — the exact shape that makes an agent conclude Danube broke and `report_tool` it. The skill now keys on the status and the message text and warns about that `code`. `references/troubleshooting.md` also names the nine hosted tools that count (Screenshot doesn't), notes that calling them directly with `…
Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.
These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.
sha256:19feed51605c88b1a13a4806abe60936cc69a02347ed6b5547c128fa6f111e78sha256:e244f2777e6034c9ee39476d8bab4d60c85a7850d3ba55d868f39094281ff81a