skills/iliaal/ai-skills/cpp-systems/Gen Agent Trust Hub

cpp-systems

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and refactor C++ source files and build configurations, which serves as an ingestion point for untrusted data from a codebase.
  • Ingestion points: SKILL.md defines a broad range of C++ and CMake file extensions for analysis.
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious directions embedded within code comments or string literals.
  • Capability inventory: As a coding assistant skill, the agent performs file analysis and modification, and may interact with build tools based on the content of these files.
  • Sanitization: No explicit sanitization or filtering of input data from source files is described.
  • [EXTERNAL_DOWNLOADS]: The references/cmake-and-tooling.md file describes the use of FetchContent and Git submodules for managing dependencies, which involves fetching external source code during the build process.
  • [COMMAND_EXECUTION]: The SPEC.md document specifies the execution of a local Python script (distillery/scripts/distiller.py) for the purpose of validating and testing the skill's trigger patterns and overall functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 10:36 AM
Security Audit — agent-trust-hub — cpp-systems