The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform shell-based operations using git to resolve branch references and retrieve code differences. Specifically, it uses git merge-base and git diff to identify the changes requiring review.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data in the form of code changes from potentially external contributors. It lacks specific boundary markers or instructions to the agent to disregard instructions that might be embedded within code comments or documentation files being reviewed.
Ingestion points: Code changes retrieved via git diff and the content of the quality_scale.yaml file.
Boundary markers: The skill does not provide delimiters or "ignore embedded instructions" warnings for the content it analyzes.
Capability inventory: The skill has the capability to spawn up to 10 parallel subagents and invoke the ha-quality-scale-verify skill to perform further analysis based on the ingested content.
Sanitization: No evidence of sanitization or filtering of the external code content before analysis is provided.

ha-review