huawei-cloud-swr-image-governance

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to execute hcloud CLI commands to manage cloud resources (SWR namespaces, repositories, and permissions). This is the core functionality and is used within the intended scope of cloud governance.
  • [PROMPT_INJECTION]: The skill processes external data retrieved from Huawei Cloud services, which constitutes a surface for indirect prompt injection.
  • Ingestion points: Data is ingested via CLI command outputs such as hcloud SWR ShowNamespaceAuth and hcloud SWR ListRetentions in SKILL.md and related task files.
  • Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore instructions embedded in the retrieved cloud metadata (e.g., user names or repository descriptions).
  • Capability inventory: The skill possesses capabilities to create, update, and delete cloud resources using the hcloud tool as described in references/task-namespace-permissions.md and other task files.
  • Sanitization: There is no mention of sanitizing or validating the output from the CLI tools before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 09:10 AM
Security Audit — agent-trust-hub — huawei-cloud-swr-image-governance