mcp-cli
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documents the use of
mcp-clito execute tools provided by MCP servers. Examples include filesystem operations (read_file,search_files) and piping outputs through standard utilities likejqandxargs. These are standard functional requirements for the skill's purpose. - [INDIRECT_PROMPT_INJECTION]: The skill functions as a gateway to external data sources (GitHub, databases, APIs). While it lacks explicit boundary markers or sanitization logic in the documentation, it does not contain instructions to override safety filters or follow hidden commands within that data. The vulnerability surface is inherent to the Model Context Protocol's design rather than a specific malicious instruction in this skill.
- [DYNAMIC_EXECUTION]: The documentation provides an example of dynamic command construction using
xargs -I {} sh -c. This pattern is used for automating file reads based on search results. As this is a standard developer workflow example provided by the vendor, it is considered safe in this context.
Audit Metadata