The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the rwx CLI tool for tasks such as fetching reference documentation (rwx docs pull) and validating generated configurations (rwx lint). These operations are consistent with the skill's primary purpose of migrating workflows to the vendor's platform.
[DATA_EXPOSURE]: The skill identifies and inventories sensitive workflow components, such as secrets and environment variables, to ensure they are correctly mapped during migration. This analysis is performed locally for documentation purposes and does not involve exfiltration to external domains.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted GitHub Actions workflow files. While this creates a potential surface for indirect injection, the risk is mitigated by the skill's focus on structured translation and the use of a formal linter (rwx lint) to validate the resulting configuration before finalization.
[METADATA_POISONING]: Metadata fields (name, version, description) are descriptive and consistent with the underlying instructional logic, showing no signs of deceptive or malicious content.

migrate-from-gha