The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes git diff and git log commands to identify changed files and verify the chronological order of test and implementation commits for TDD assessment.
[PROMPT_INJECTION]: The skill exhibits an inherent vulnerability surface for indirect prompt injection because it reads and processes untrusted source code provided by users.
Ingestion points: Local implementation files and git diff outputs analyzed during the review process.
Boundary markers: The instructions do not specify delimiters or constraints to prevent the agent from obeying instructions embedded within the reviewed code.
Capability inventory: The skill has access to local file system reading and shell command execution via git.
Sanitization: There is no logic provided to sanitize or filter the code content before it is processed by the agent.

quality-reviewer