mo-auth
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the
moclibinary (e.g.,mocli auth init,mocli auth info) to manage authentication states and retrieve user profile information. This is the intended primary functionality for a CLI-based authentication skill. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data in the form of user profile information (name, intro) returned by the
moclicommand. - Ingestion points: Data is received via the
mocli auth info --profilecommand output. - Boundary markers: The skill does not define technical boundary markers for the CLI output but provides explicit natural language instructions on how the agent should handle and display the data.
- Capability inventory: Capabilities are restricted to executing the specific
mocliauthentication subcommands. - Sanitization: The skill mandates the masking of the
api_keyfield in all responses and provides guidance on which profile fields are safe to display.
Audit Metadata