add-custom-domain
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs project and domain management tasks by executing commands via the @temps-sdk/cli utility and the dig network tool.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-defined inputs like domains and project IDs which are interpolated into shell commands.
- Ingestion points: User-provided instance URLs, project IDs, domain names, and worker IDs in SKILL.md.
- Boundary markers: None.
- Capability inventory: Shell command execution via bunx @temps-sdk/cli and dig in SKILL.md.
- Sanitization: The skill uses double quotes for the instance URL parameter in the login command, providing some protection against basic shell injection.
Audit Metadata