huawei-cloud-cloudrobo-workspace

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the hw-cloudrobo-client PyPI package. This is a vendor-provided resource necessary for the skill's primary function of managing cloud resources.\n- [COMMAND_EXECUTION]: The skill logic and the included scripts/test-cli-commands.sh script perform numerous calls to the cloudrobo CLI. These commands manage workspace resources and members. Mutation commands are guarded by user confirmation instructions in the documentation.\n- [DYNAMIC_EXECUTION]: The testing utility scripts/test-cli-commands.sh uses python3 -c to execute SDK-based verification code. This allows for automated testing of the WorkspaceClient within the user's environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided inputs such as workspace names and descriptions which are interpolated into CLI commands. While the skill documentation specifies strict server-side validation regex (e.g., ^[\u4e00-\u9fa5a-zA-Z0-9-_./]{3,64}$), these fields constitute an ingestion surface for indirect prompt injection. Mandatory Evidence Chain: 1. Ingestion points: workspace create --name, workspace update --description (in SKILL.md). 2. Boundary markers: None explicitly used in command interpolation. 3. Capability inventory: Shell command execution via cloudrobo CLI and local file writes to ~/.cloudrobo/workspace.json. 4. Sanitization: Server-side regex validation is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 06:42 AM
Security Audit — agent-trust-hub — huawei-cloud-cloudrobo-workspace