The Agent Skills Directory

[SAFE]: The skill's content is entirely instructional, focusing on accessibility guidelines for web links. Analysis of the text and code snippets found no evidence of malicious behavior, obfuscation, or unauthorized data access.
[EXTERNAL_DOWNLOADS]: The skill metadata and content reference documentation from frontendchecklist.io. These are neutral references to a well-known educational resource for web development standards.
[PROMPT_INJECTION]: The skill instructs the agent to review external HTML and components, which constitutes a surface for indirect prompt injection. However, because the skill has no capabilities to write to the file system or perform network operations, the security risk is negligible.
Ingestion points: Rendered HTML and interactive components (SKILL.md)
Boundary markers: Absent
Capability inventory: No dangerous tools, shell access, or file-writing operations are requested or used
Sanitization: Absent

empty-links