.claude/skills/mcp-security-scanRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
当用户说『接了个MCP server不放心』『MCP工具能执行命令怕有风险』『怎么审计MCP权限』『第三方MCP会不会偷数据』,或要把某 MCP server(模型上下文协议)接进 agent、担心它是新攻击面时使用。把 MCP server 当『需审查的第三方』:扫工具清单里的 命令执行/文件系统写/网络外联/凭证暴露 四类风险,给风险评级与最小授权建议。理论根基:LGD 三律(有籍·有证·有门禁)。触发词:MCP安全、mcp security、MCP审计、MCP权限、第三方MCP、MCP风险、server扫描、协议安全。
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/mcp-security-scanRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/mcp-security-scanRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/mcp-security-scanRuntime, 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 @zhaoxinghua09-cell/mcp-security-scanclawhub inspect @zhaoxinghua09-cell/mcp-security-scan --version 1.0.4This 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:cb94be4577a0d5be3a7d60507dcd32c2e250bc72591832d4bad45a7f8f3e41bcAGENTS.mdicon.pnglgd-powered.pngllms.txtREADME.mdscripts/mcp_scan.pyskill-card.mdSKILL.md- Major restructuring: documentation and metadata refactored for clarity and compliance. - Added AGENTS.md, icon assets, and llms.txt; removed several legacy docs. - SKILL.md now fully bilingual (English/Chinese), focused, and much shorter. - Clearer input/output schema and permission declarations in skill metadata. - Updated risk rationale, changelog, and classification fields. - Documentation updated to reflect actual security review coverage and usage workflow.
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.
sha256:55480c7736d1ce8b82eb8dc4a5999e5eae6543d91ba7db7319d0a0ccabcbd6ddsha256:069ef478fb2332131375251ed7bc340a4fc9200dd3dcef669f64b68f4fe4fa8f