The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content, specifically rendered HTML and interactive design patterns, creating a surface for indirect prompt injection. * Ingestion points: The skill instructs the agent to review 'rendered HTML, interactive components, or design-system patterns' (SKILL.md). * Boundary markers: The instructions do not define specific delimiters or warnings to prevent the agent from following instructions embedded within the analyzed HTML. * Capability inventory: The skill's actions are restricted to code review, flagging violations, and providing explanations; it does not request capabilities for file writing, network communication, or command execution. * Sanitization: There are no instructions for sanitizing or escaping the user-provided code before analysis.
[SAFE]: The skill references an external resource from frontendchecklist.io, which is a well-known and reputable source for web development and accessibility standards.

audio-descriptions