The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill provides frameworks and reference materials for usability, accessibility, and cultural UX considerations based on established industry standards.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the analysis of user-provided interface content, which presents a surface for indirect injection.
Ingestion points: User-supplied design descriptions, interface copy, and navigation labels referenced in SKILL.md.
Boundary markers: None present; the skill lacks delimiters or instructions to ignore embedded commands in audited text.
Capability inventory: The skill is strictly textual and does not request tool permissions or perform file system or network operations.
Sanitization: No sanitization or filtering of external input is defined.
[METADATA_POISONING]: The author field in the SKILL.md frontmatter (wondelai) does not match the provided author context (aaaaqwq). This metadata inconsistency is minor and likely represents a reused template rather than an attempt to deceive.

ux-heuristics