issue-fields-migration
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to perform read and write operations on repository and organization metadata. These commands are integral to the migration process and are executed with user oversight. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources (labels and project fields) which could contain malicious instructions. It mitigates this risk via a comprehensive evidence chain: (1) Ingestion points: labels and project items; (2) Boundary markers: mandatory user confirmation of mappings and a full pre-execution summary; (3) Capability inventory: REST API write access and label deletion; (4) Sanitization: URL-encoding of label names to prevent path traversal or injection.
- [DYNAMIC_EXECUTION]: The skill facilitates the generation of shell scripts for processing large batches of items. This approach provides transparency by allowing the user to review the exact commands before they are executed manually in their local environment.
Audit Metadata