The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches necessary framework components and utilities from the npm registry during project initialization. It also references a public CDN (cdnjs.cloudflare.com) to load the axe-core library for accessibility auditing and uses the OpenRouter API for image enhancement tasks.- [COMMAND_EXECUTION]: The agent is required to execute various shell commands to set up the development environment, manage dependencies, and initialize the project structure. Additionally, the skill instructs the agent to dynamically generate and run scraping scripts in Phase 2 to extract content from existing websites.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its data processing workflow.
Ingestion points: In Phase 2 and Phase 11a, the agent is instructed to visit and scrape all text and metadata from user-provided URLs and competitor websites.
Boundary markers: The instructions do not specify the use of delimiters or warnings to separate scraped content from the agent's instructions.
Capability inventory: The agent possesses significant capabilities, including the ability to write files to the local directory, execute shell commands, and push code to remote repositories.
Sanitization: There is no requirement or method specified for sanitizing or filtering the content retrieved from external sites before it is processed by the agent.

website-rebuild