.claude/skills/skill-authorRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Author, harden, and publish agent skills for ClawHub — write skills that conform to ClawHub conventions (frontmatter, structure, naming, versioning, licensing), run pre-publish hardening, and remediate clawhub.ai security-audit findings. Use when creating a skill for ClawHub, preparing a new version to publish, or when given a clawhub.ai/<owner>/<slug>/security-audit page.
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/skill-authorRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/skill-authorRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/skill-authorRuntime, 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 @sunshinejnjn/skill-authorclawhub inspect @sunshinejnjn/skill-author --version 1.2.3This 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.
sha256:113e8da0cc1229343c257c518a3b0658a135eee8280e849030461a45b3fbfbb0LICENSEREADME.mdreferences/audit-patterns.mdreferences/authoring-guide.mdreferences/publish-checklist.mdskill-card.mdSKILL.mdVERSION1.2.3: Added a declared-permissions block to SKILL.md frontmatter that factually separates what this package ships (documentation only: Markdown/LICENSE/VERSION, no executable code) from what an operator who follows the guide will actually do (network fetch of a security-audit page, clawhub CLI calls, file edits, and operator-run shell snippets each targeting paths the operator chooses). Also folded the skill-author 1.2.0->1.2.1 remediation experience into references/audit-patterns.md as a worked case.
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:e680431dd6404d5a2ecf80349aea277130e9e6dd3f51c6f4d0fadb8f3257fac2