compute-llk-bringup

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines procedures for executing local scripts such as scripts/find_symbol.py, scripts/gen_structure.py, and scripts/run_ttnn_pytests.sh to facilitate the development and verification of compute kernels.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and extract logic from upstream header files and implementation source code. This represents a data ingestion surface, but it is restricted to the local development environment and project repository.
  • [DYNAMIC_EXECUTION]: The skill involves managing Just-In-Time (JIT) compilation processes for hardware kernels, which includes triaging compiler output and inspecting dynamically generated source files for debugging purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:03 PM