external-gitcode-ascend-ascendc-operator-dev

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is synchronized from an official repository on GitCode (gitcode.com/Ascend/agent-skills). This source is recognized as a well-known service associated with the official Ascend development platform.
  • [COMMAND_EXECUTION]: The skill utilizes standard shell commands to manage development environments and build processes.
  • Executes source ${CANN_PATH}/*/set_env.sh and conda activate to initialize the necessary development environments.
  • Orchestrates the execution of ./build.sh and pip install to compile and install generated operator packages in Phase 4.
  • [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection through user-provided operator requirements.
  • Ingestion points: Operator names and functional descriptions are collected as mandatory input in Phase 0.2 (SKILL.md).
  • Boundary markers: The workflow does not explicitly define delimiters or instructions to ignore embedded commands within user input.
  • Capability inventory: The orchestrator has the capability to modify the file system, execute build scripts, and run profiling tools like msprof across its seven phases.
  • Sanitization: There are no documented sanitization or validation steps for the input strings before they are used in code generation or documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 03:04 AM
Security Audit — agent-trust-hub — external-gitcode-ascend-ascendc-operator-dev