Skills
skills/ascend/agent-skills/vector-triton-ascend-ops-optimizer/Gen Agent Trust Hub

vector-triton-ascend-ops-optimizer

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands for environment configuration (source, export), testing (pytest), and performance profiling (msprof). These operations target official Huawei toolkit paths (e.g., /usr/local/Ascend/) and are necessary for its primary function.
  • [PROMPT_INJECTION]: The skill processes and executes user-provided code files (<op_name>.py). This represents an indirect prompt injection surface that is inherent to code-optimization tools.
  • Ingestion points: Local Python operator and test files.
  • Boundary markers: None.
  • Capability inventory: Execution of pytest and msprof.
  • Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 06:48 AM