Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/23/2026.claude/skills/skill-release-auditRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Real Skill packageSource verifiedClawHub registry
skill-release-audit
Pre-publish quality and safety auditor for AI agent skills (SKILL.md + scripts/ + references/ format used by Claude Code, Cursor, OpenAI Codex, GitHub Copilot, OpenClaw, ClawHub, and compatible SkillHub registries). Six static-check modules (no LLM, no network by default): (1) syntax and logic correctness, (2) feature completeness, (3) edge-case and error handling, (4) data safety (detects files written inside the skill dir that would be lost on update), (5) dependency declaration vs code, (6) SKILL.md documentati…
Identity and source
Publisher attributionEvan Songregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 68% rule confidence
Package forminstruction with code31 recorded files
Canonical sourceClawHub registryclawhub:songhonglei:skill-release-audit
Platform declarations
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
OpenClawnative officialProvenance: registry distribution
Independent structural checks
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/23/2026.agents/skills/skill-release-auditRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/23/2026skills/skill-release-auditRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Installation and inspection
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 @songhonglei/skill-release-auditclawhub inspect @songhonglei/skill-release-audit --version 1.2.0Security evidence
SkillVetAI static result: no findings detected
This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
- Status
- completed
- Coverage
- full text content
- Files
- 31 / 31 inspected as text
- Checked
- 9/23/2026, 1:28:05 PM
- Scanner
- 0.1.3
- Policy
- 1.0.3
6 inferred permission indicators
- shell execution — automatically inferred
- network access — automatically inferred
- filesystem read — automatically inferred
- filesystem write — automatically inferred
- credential access — automatically inferred
- external write action — automatically inferred
7 dependency and API indicators
- api: clawhub.ai
- api: docs.docker.com
- api: github.com
- api: nodejs.org
- api: pandoc.org
- api: pypi.org
- api: www.npmjs.com
External clawhub result: clean
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.
- Evidence checked
- 9/22/2026, 12:52:08 PM
- Release binding
- Matches this record
- vt: clean
- skillspector: suspicious
- llm: clean
Recorded files
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
Package content hash
sha256:a1beaf68a24ed0bff59db028af6e44bd5c5f7e601e5bfb598c9e48814adf20caShow up to 30 recorded paths
config/env_contracts.jsonprofiles/anthropic.jsonprofiles/clawhub.jsonprofiles/generic.jsonprofiles/github.jsonprofiles/skillhub.jsonREADME.mdreferences/dep-patterns.mdreferences/hub-specs.mdreferences/safe-paths.mdscripts/_common.pyscripts/_env_check.pyscripts/check_data_safety.pyscripts/check_deps.pyscripts/check_docs.pyscripts/check_edges.pyscripts/check_features.pyscripts/check_logic.pyscripts/healthcheck.pyscripts/i18n.pyskill-card.mdSKILL.mdtests/fixtures/env_governance/EXPECTED.mdtests/fixtures/env_governance/fixture_comment.pytests/fixtures/env_governance/fixture_js_dataflow_neg.mjstests/fixtures/env_governance/fixture_js_dataflow.mjstests/fixtures/env_governance/fixture_js.jstests/fixtures/env_governance/fixture_optional.pytests/fixtures/env_governance/fixture_required.pytests/fixtures/env_governance/fixture_runtime.py
Source changelog
Env-var false-positive governance v1.2: JS env-object data-flow tracking — alias bindings (const environment = process.env), fn(process.env) parameter propagation, Zod parse/safeParse results (schema.parse(environment), safeParse({...environment}).data), and config-loader return values (loadConfig(process.env)) now count as indirect uses filed under ENV_DECLARED_INDIRECT (console silent, JSON evidence keeps hit paths); indirect uses only affect the reverse declared-unused check, never the forward required/optional classification. Also: module-1 runtime-external path classification (~/, $HOME/, absolute paths → INFO not WARN), data-safety template exemption (example/sample/template named config files), and 8 frozen regression fixtures. Platform-neutral env contracts preserved (empty runtimeInjected — fork-specific injections stay in downstream forks).