The Agent Skills Directory

[PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by instructing the agent to ingest and act upon data from local configuration files.\n
Ingestion points: Reads vite.config.ts and package.json to determine server port configurations (SKILL.md).\n
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the configuration files are provided.\n
Capability inventory: The agent is instructed to execute grep, lsof, curl, and kill based on the data identified in those files (SKILL.md).\n
Sanitization: No sanitization or validation of the configuration file content is performed before its use in shell command templates.\n- [COMMAND_EXECUTION]: Provides shell command templates for identifying and managing local development server processes.\n
Includes patterns for using lsof to find processes on specific ports and curl for health polling.\n
Includes a pattern for terminating stalled local server instances using kill -9.\n- [EXTERNAL_DOWNLOADS]: Recommends the installation of the wait-on package from the NPM registry, a well-known utility for synchronizing with network resources.

vite-agent