The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill recommends the use of npx frontend-standard-skills to automate the installation of rules and configuration. This is a standard delivery mechanism for developer tools and is consistent with the author's identified resources.
[PROMPT_INJECTION]: The skill is designed to review and analyze source code, which serves as an ingestion point for untrusted data. This creates a surface for indirect prompt injection, as malicious instructions hidden in code comments could attempt to influence the agent's feedback.
Ingestion points: User-provided source files (e.g., components in src/components/, hooks in src/hooks/).
Boundary markers: The instructions do not specify explicit delimiters to isolate the analyzed code from the agent's logic.
Capability inventory: The skill allows the agent to read project files, write rule sets (assets/RULES.md), and perform textual analysis of code.
Sanitization: No explicit sanitization or filtering of external source code is defined within the skill instructions.

react