cpp-pro

Fail

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses CMake's FetchContent to download the well-known fmt library from its official GitHub repository and provides instructions for installing the conan package manager via pip. These resources are industry standards for C++ development.
  • [COMMAND_EXECUTION]: The skill documentation provides various shell commands for building projects with CMake, running static analysis tools like clang-tidy and cppcheck, and performing system profiling with perf and valgrind. These are standard utilities used by developers to compile, test, and optimize software.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an inherent attack surface as it is designed to ingest and process external C++ source code and build configurations. If these files were to contain malicious instructions, they could potentially influence the agent's behavior. However, the skill explicitly instructs the agent to use AddressSanitizer and UndefinedBehaviorSanitizer to detect and fix memory errors and undefined behavior, promoting a security-conscious workflow.
  • Ingestion points: C++ source files, CMakeLists.txt, and configuration files referenced in SKILL.md and references/build-tooling.md.
  • Boundary markers: The skill provides structural templates but does not specify explicit boundary delimiters for user-provided code in the reference materials.
  • Capability inventory: Local execution of build tools (CMake), static analyzers (clang-tidy), and profilers (perf, valgrind, kcachegrind) as described in references/build-tooling.md.
  • Sanitization: No explicit sanitization of input source code is defined beyond the use of standard compiler and analysis tools.
Recommendations
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Oct 3, 2026, 06:12 PM