deploy-to-cloud-engine
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
icpcommand-line interface for critical operations including identity management (icp identity link web), deployment (icp deploy), and cycles management. These are standard and documented operations for the Internet Computer ecosystem. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data from local files, which represents an indirect prompt injection surface.
- Ingestion points: Project versioning and build metadata are extracted from
package.jsonand deployment configurations are read fromicp.yaml. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the ingested data.
- Capability inventory: The skill possesses capabilities for shell command execution and network deployment.
- Sanitization: No explicit sanitization or validation of the strings read from the project files is described before they are used in command interpolation or build configurations.
Audit Metadata