cloudbase-mcp
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external tool outputs and schemas via the
mcportertool, which presents an attack surface for indirect prompt injection. - Ingestion points: The agent is instructed to read tool schemas and call tools using
mcporter describeandmcporter call, as documented inSKILL.md. - Boundary markers: There are no instructions or delimiters specified to help the agent distinguish between its own instructions and potentially malicious content embedded in tool outputs or schemas.
- Capability inventory: The skill utilizes shell command execution (
npx,mcporter) and interacts with cloud environments via remote endpoints (specified inSKILL.md). - Sanitization: The instructions do not define any validation or sanitization procedures for the data retrieved from external tools.
- [COMMAND_EXECUTION]: The skill requires the execution of several shell commands for setup and operation, including
npx @cloudbase/cloudbase-mcp@latest,mcporter list, andpnpm install(for contributors). - [EXTERNAL_DOWNLOADS]: The skill uses
npxto fetch and run the@cloudbase/cloudbase-mcppackage from the NPM registry. It also provides links to official GitHub and domestic mirror repositories for the source code and documentation.
Audit Metadata