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 mcporter tool, which presents an attack surface for indirect prompt injection.
  • Ingestion points: The agent is instructed to read tool schemas and call tools using mcporter describe and mcporter call, as documented in SKILL.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 in SKILL.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, and pnpm install (for contributors).
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and run the @cloudbase/cloudbase-mcp package from the NPM registry. It also provides links to official GitHub and domestic mirror repositories for the source code and documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 03:14 PM