The Agent Skills Directory

[SAFE]: The skill is designed for static analysis of frontend code and performs all operations locally using git commands without requiring network access or sensitive credentials.- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it processes untrusted content from git diffs. This is an inherent property of code review tools and is mitigated by the lack of dangerous execution tools.
Ingestion points: Untrusted data enters the context via the git diff main...HEAD command described in SKILL.md.
Boundary markers: The skill does not specify any boundary markers to distinguish diff content from instructions.
Capability inventory: No file system writing, network requests, or subprocess execution capabilities are present in the skill instructions.
Sanitization: No sanitization is performed on the incoming diff data before it is analyzed by the agent.

pr-review-frontend