skills/alismx/claude-skills/cpp-pro/Gen Agent Trust Hub

cpp-pro

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's build system reference (references/build-tooling.md) includes examples of using CMake's FetchContent to download the well-known fmt library from its official GitHub repository. This represents standard and safe dependency management in modern C++ development.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided C++ source code and build configurations to perform tasks like static analysis, debugging, and performance profiling.
  • Ingestion points: User-supplied C++ source files (.cpp, .h) and CMake configuration scripts analyzed in the core workflow (SKILL.md).
  • Boundary markers: None explicitly defined to separate user-provided code content from the agent's analysis instructions.
  • Capability inventory: The workflow utilizes various CLI tools including cmake, clang-tidy, cppcheck, perf, and valgrind for code processing.
  • Sanitization: The skill relies on standard tool-based validation and does not specify additional sanitization for user-provided paths or code inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 11:04 PM