litium-cloud-migration
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous shell commands for repository inventorying, using tools like
grep,find, andlsto analyze project structure, dependencies, and configuration for Linux compatibility. It also coordinates deployment and environment management through thelitium-cloud-cliextension. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface as it reads a persistent state file (
MIGRATION.md) from the user's repository to manage migration progress across multiple sessions. - Ingestion points: Reads
MIGRATION.mdfrom the root of the customer repository during the session initialization. - Boundary markers: The skill does not employ specific boundary markers for the data read from the state file, relying on the agent's interpretation of the Markdown template.
- Capability inventory: The skill can execute local shell commands for file analysis and use the
litium-cloudCLI for application lifecycle management, including deletion and deployment. - Sanitization: The skill includes explicit instructions for the agent to avoid writing secrets to shared files and requires human-in-the-loop confirmation for any production-altering actions.
Audit Metadata