The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions require the agent to execute git diff and read the repository styleguide to perform its review. These are standard, low-risk read-only commands for a code analysis tool.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it processes untrusted source code data. * Ingestion points: The agent ingests output from git diff and the content of the .gemini/styleguide.md file. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the analyzed code are provided. * Capability inventory: The skill is limited to reading repository state, performing analysis, and invoking sub-agents; it lacks capabilities for network access or arbitrary file modifications. * Sanitization: There is no validation or sanitization of the ingested code content before it is processed for review.

code-review