build
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted content such as source code and build configuration files.
- Ingestion points: User-supplied source code, Makefiles, CMakeLists.txt, and other build-related configuration files mentioned in SKILL.md.
- Boundary markers: The instructions do not define delimiters or explicit warnings to ignore instructions embedded in the processed data.
- Capability inventory: The agent is instructed to use build systems (Make, CMake, Gradle), compilers (gcc, rustc), and package managers (npm, Cargo) which involve shell execution.
- Sanitization: There are no documented mechanisms for sanitizing or validating the input data before it is processed by the build tools.
- [COMMAND_EXECUTION]: The core functionality of the skill is centered around the execution of build automation tools and system commands necessary for compilation and packaging.
- [DYNAMIC_EXECUTION]: The skill facilitates native compilation and asset optimization, which involves transforming source code into executable artifacts at runtime.
Audit Metadata