skills/alexai-mcp/hermes-ccc/mcporter/Gen Agent Trust Hub

mcporter

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Recommends the installation of the 'fastmcp' library from the official Python Package Index (PyPI).
  • [COMMAND_EXECUTION]: Includes example code for executing shell commands like 'grep' and 'git' via the Python subprocess module. These examples follow security best practices by using list-based argument passing.
  • [PROMPT_INJECTION]: Describes patterns for tools that process untrusted external data and interpolate it into prompts. This describes a potential indirect prompt injection surface.
  • Ingestion points: The skill documents tools that fetch URL content (fetch_url), read local files (read_file), and process code snippets (code_review_prompt).
  • Boundary markers: Code blocks are used for formatting in prompt templates, but no explicit 'ignore-instructions' directives are included in the examples.
  • Capability inventory: The server examples include capabilities for shell execution, file system access, and network communication.
  • Sanitization: Input validation or sanitization logic is not provided in the code samples.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 05:24 PM
Security Audit — agent-trust-hub — mcporter