The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands including 'git log', 'git diff', and 'bun run check'. These are standard development tools used for code analysis and verification within the intended environment.
[PROMPT_INJECTION]: As a code review tool, the skill processes untrusted code inputs from the repository or user, representing an indirect prompt injection surface. Evidence chain: (1) Ingestion points: git history and local files; (2) Boundary markers: Not present in methodology; (3) Capability inventory: Subprocess calls via 'git' and 'bun'; (4) Sanitization: No explicit content filtering. This risk is inherent to the skill's primary function and is mitigated by typical LLM safety constraints.

code-review