huawei-cloud-business-support-query

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The scripts/ensure_env.py script downloads the get-pip.py setup utility from well-known and official sources, including bootstrap.pypa.io and Huawei Cloud's official mirrors, to ensure the environment has a functional package manager.
  • [COMMAND_EXECUTION]: The environment preparation scripts (check_env.sh, check_env.ps1, and ensure_env.py) use shell commands to install system-level dependencies, manage Python virtual environments, and install the required Huawei Cloud SDK packages.
  • [COMMAND_EXECUTION]: scripts/ensure_env.py uses os.execv for process replacement to transition execution into the newly created Python virtual environment, which is a standard practice for ensuring dependency isolation.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external data from cloud APIs.
  • Ingestion points: Data returned from various Huawei Cloud billing and resource APIs across the query scripts.
  • Boundary markers: No explicit delimiters are used to separate API-returned data from agent instructions.
  • Capability inventory: Subprocess execution and process replacement capabilities are present in the environment setup script (scripts/ensure_env.py).
  • Sanitization: API responses are processed and output without explicit filtering for embedded natural language instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 01:44 AM
Security Audit — agent-trust-hub — huawei-cloud-business-support-query