The Agent Skills Directory

[PRIVILEGE_ESCALATION]: The SKILL.md file contains instructions for the agent to execute sudo apt update && sudo apt install python3 on Linux systems. This allows the agent to acquire administrative privileges on the host environment during the initial setup of the skill's requirements.
[COMMAND_EXECUTION]: The skill requires the agent to execute shell commands, including running local Python scripts (scripts/search.py) and using system package managers (brew, apt, winget).
[INDIRECT_PROMPT_INJECTION]: The skill processes data from multiple CSV files to provide design recommendations, which the agent is then instructed to synthesize into implementation code. This represents a vulnerability surface where modified source data could influence the agent's output.
Ingestion points: Data is read from reference CSV files in the data/ directory.
Boundary markers: The instructions do not define clear boundaries or validation steps for the content retrieved from these files.
Capability inventory: The agent has the capability to execute shell commands as part of the skill's defined workflow.
Sanitization: The search script does not sanitize the CSV field content before it is provided to the agent.
[EXTERNAL_DOWNLOADS]: The skill includes links to official documentation and external font assets from well-known and trusted platforms.
References include Google Fonts for typography and official documentation for frameworks like Tailwind CSS, React, Next.js, Vue, Svelte, SwiftUI, Flutter, and React Native.

ui-ux-pro-max