The Agent Skills Directory

[SAFE]: The skill serves as a guide for ensuring unique IDs in HTML, which is a standard best practice for web accessibility and functionality.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes HTML markup provided by the user. While this ingestion of external data is a potential attack surface for indirect prompt injection, the skill's instructions are narrowly focused on ID uniqueness, and it lacks the high-risk capabilities (like network access or command execution) necessary for a dangerous exploit.
Ingestion points: User-provided HTML documents, templates, or shared components analyzed during code review.
Boundary markers: The instructions do not define specific delimiters to separate the HTML data from the agent's instructions.
Capability inventory: The agent is restricted to analyzing, flagging, explaining, and fixing HTML markup. No shell execution, file system writes, or network operations are involved in the skill's logic.
Sanitization: No explicit sanitization or filtering of the input HTML is described.
[EXTERNAL_DOWNLOADS]: The skill contains links to informational resources and validation tools, such as frontendchecklist.io and the W3C Markup Validator (validator.w3.org), for documentation and validation purposes.

unique-id