The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes several shell commands to facilitate the code review process. It uses git diff to identify changes, grep to detect technology stacks, and executes ruff, mypy, and pytest on the local codebase. The use of pytest in the post-fix verification step involves the dynamic execution of local Python code.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) because its primary function is to ingest and analyze untrusted data (source code from a repository).
Ingestion points: Python source files (.py) and git diff outputs are read into the agent's context for review.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent processes the code content.
Capability inventory: The skill can execute shell commands (ruff, mypy, pytest), access the file system, and load additional specialized skills using the Skill tool.
Sanitization: No sanitization or filtering of the ingested code content is mentioned before it is processed by the model for analysis.

review-python