The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to run the project's canonical test suite and static analysis tools to verify code changes. These commands are executed in the local environment and are determined by the project configuration.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes several untrusted data sources from the repository.
Ingestion points: Reads spec.json, requirements.md, design.md, tasks.md, and implementer status reports, as well as code content via git diff.
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested files.
Capability inventory: The skill possesses the ability to execute shell commands for version control, testing, and linting.
Sanitization: There are no requirements to sanitize or validate the content of the files before the agent processes them.

kiro-review