skills/ascend-ai-coding/awesome-ascend-skills/external-gitcode-ascend-triton-operator-env-config/Gen Agent Trust Hub
external-gitcode-ascend-triton-operator-env-config
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the Miniconda installer from official Anaconda repositories (
repo.anaconda.com) and specific PyTorch wheels fromdownload.pytorch.org. - [REMOTE_CODE_EXECUTION]: Setup instructions include downloading and executing shell scripts for Miniconda installation (
bash Miniconda3-latest-Linux-*.sh). - [COMMAND_EXECUTION]: The skill executes several shell commands for environment configuration, including sourcing CANN setup scripts (
set_env.sh), checking NPU status (npu-smi), and usingpipfor package installation. - [COMMAND_EXECUTION]: The troubleshooting section includes instructions to install system-level build dependencies (such as
g++,zlib1g-dev, andclang-15) usingsudo apt install. - [COMMAND_EXECUTION]: A local Python script (
scripts/01-vector-add.py) is executed to verify that the Triton environment and NPU acceleration are functioning as expected. - [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection by instructing the agent to read and follow requirements from external documentation at
triton-ascend.readthedocs.io. - Ingestion points: Official online documentation for version matching and installation guides.
- Boundary markers: Absent; the agent is directed to read the entire page without specific delimiters.
- Capability inventory: The skill has access to file system writes, package installation (
pip,apt), and network downloads (wget). - Sanitization: None; the agent is expected to extract and apply version numbers and instructions directly from the documentation.
Audit Metadata