The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute system commands like git diff and git status to identify modified files for review.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data (source code and requirements documents) without explicit sanitization or strict boundary markers.
Ingestion points: Reads project source code and requirement files from the context/ directory.
Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded commands within the code being reviewed.
Capability inventory: The skill possesses the ability to read project files, execute git commands, and write review reports back to the filesystem.
Sanitization: No logic is present to escape or validate the content of the files before they are processed by the agent.

code-reviewer