infrahub-teaching-concepts
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The tutor reads and interprets user-supplied schema and object files to customize lesson content. This creates a theoretical vector where malicious instructions inside those files could attempt to override the tutor's behavior.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to run the 'infrahubctl' command-line interface. This is used to validate learner-authored files and reference solutions, ensuring exercises are solvable within the defined learning workspace.
Audit Metadata