globalize-now-cli-use
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external repositories during discovery and detection phases, creating a surface for indirect prompt injection.
- Ingestion points: Repository metadata and file structures retrieved via
git remote get-urland the detection commands (github detect,gitlab detect) in SKILL.md. - Boundary markers: The instructions lack explicit boundary markers or warnings to ignore embedded instructions in the detected repository data.
- Capability inventory: The skill can perform network operations and modify project states using
npx @globalize-now/cli-client. - Sanitization: No specific sanitization or validation of the repository-sourced data is described.
- [COMMAND_EXECUTION]: The skill instructs the agent to run
gitandnpx @globalize-now/cli-clientcommands. It includes a mandatory user confirmation step before connecting repositories.
Audit Metadata