univer-workspace-cli
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the
univer-workspace-clipackage globally using npm. This package is the primary subject of the skill and originates from the tool's vendor. - [COMMAND_EXECUTION]: The skill provides various commands for the agent to execute, including configuration setup, authentication workflows, and interacting with the Workspace API. These are standard operations for the tool's intended use.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a mechanism for the agent to load additional operational instructions dynamically from the installed CLI via
univer-workspace-cli skills get. While this represents an ingestion of external content into the agent's context, it is the tool's intended modular design for providing version-matched guidance. - Ingestion points: Instructions are retrieved at runtime through the
skills getandskills readcommands. - Boundary markers: The skill advises following the loaded guidance for authoring and verification but does not specify explicit sanitization steps for the retrieved content.
- Capability inventory: The agent is empowered to execute CLI commands, handle authentication codes, and perform document operations based on the retrieved guidance.
- Sanitization: Not explicitly mentioned; the agent relies on the integrity of the installed CLI tool.
Audit Metadata